AI Workflow MCP

Models

500 / 500
A
Claude Opus 4.7
by anthropic|2025-12-01|1M context

Claude Opus 4.7 supports text, image input and text output with 1M context, suited for coding agent, vision qa, reasoning.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Coding agentVision QAReasoningLong context+4
A
Claude Sonnet 4.6
by anthropic|2025-10-01|1M context

Claude Sonnet 4.6 supports text, image input and text output with 1M context, suited for coding agent, vision qa, reasoning.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Coding agentVision QAReasoningLong context+4
A
Claude Haiku 4.5
by anthropic|2025-08-01|200K context

Claude Haiku 4.5 supports text, image input and text output with 200K context, suited for coding agent, vision qa, long context.

$1 /M input$5 /M outputspeed —synced 2026-05-13
Coding agentVision QALong contextMultimodal+2
A
Qwen3 Coder
by alibaba|2025-04-01|262K context

Qwen3 Coder supports text input and text output with 262K context, suited for coding agent, long context, cheap batch.

$0.4 /M input$1.6 /M outputspeed —synced 2026-05-13
Coding agentLong contextCheap batchtool_use
B
ERNIE X1 Turbo
by baidu|2025-04-01|32K context

ERNIE X1 Turbo supports text input and text output with 32K context, suited for coding agent, reasoning, cheap batch.

$0.14 /M input$0.56 /M outputspeed —synced 2026-05-10
Coding agentReasoningCheap batchtool_use+1
B
ERNIE 4.5 Turbo
by baidu|2025-03-01|128K context

ERNIE 4.5 Turbo supports text input and text output with 128K context, suited for coding agent, cheap batch, tool_use.

$0.11 /M input$0.45 /M outputspeed —synced 2026-05-10
Coding agentCheap batchtool_use
A
Qwen Plus
by alibaba|2024-12-01|1M context

Qwen Plus supports text input and text output with 1M context, suited for coding agent, long context, cheap batch.

$0.4 /M input$1.2 /M outputspeed —synced 2026-05-13
Coding agentLong contextCheap batchtool_use
A
Qwen Turbo
by alibaba|2024-12-01|1M context

Qwen Turbo supports text input and text output with 1M context, suited for coding agent, long context, cheap batch.

$0.05 /M input$0.2 /M outputspeed —synced 2026-05-13
Coding agentLong contextCheap batchtool_use
A
Qwen3 VL
by alibaba|2024-12-01|128K context

Qwen3 VL supports text, image input and text output with 128K context, suited for coding agent, vision qa, multimodal.

$0.7 /M input$2.1 /M outputspeed —synced 2026-05-10
Coding agentVision QAMultimodalvision+1
0
Yi Large
by 01.ai|2024-09-01|33K context

Yi Large supports text input and text output with 33K context, suited for coding agent, tool_use.

$3 /M input$3 /M outputspeed —synced 2026-05-13
Coding agenttool_use
0
Yi Vision
by 01.ai|2024-09-01|16K context

Yi Vision supports text, image input and text output with 16K context, suited for vision qa, multimodal, vision.

$0.86 /M input$0.86 /M outputspeed —synced 2026-05-10
Vision QAMultimodalvision
A
Qwen Max
by alibaba|2024-09-01|33K context

Qwen Max supports text input and text output with 33K context, suited for coding agent, tool_use.

$1.6 /M input$6.4 /M outputspeed —synced 2026-05-13
Coding agenttool_use
0
Yi-Lightning
by 01.ai|1970-01-01|0K context

Yi-Lightning supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
1
Redwood AI
by 1x|1970-01-01|0K context

Redwood AI supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
1
1X World Model
by 1x|1970-01-01|0K context

1X World Model supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
3
360Zhinao3-7B-O1.5
by 360-security-technology|1970-01-01|0K context

360Zhinao3-7B-O1.5 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
3
360zhinao2-o1
by 360-security-technology|1970-01-01|0K context

360zhinao2-o1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
3
360gpt2-pro
by 360-security-technology|1970-01-01|0K context

360gpt2-pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
3
360Zhinao2-7B
by 360-security-technology|1970-01-01|0K context

360Zhinao2-7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
4
Zhiyan (智言)
by 4paradigm|1970-01-01|0K context

Zhiyan (智言) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Firefly Image 4
by adobe|1970-01-01|0K context

Firefly Image 4 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Firefly Image 4 Ultra
by adobe|1970-01-01|0K context

Firefly Image 4 Ultra supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Firefly Video
by adobe|1970-01-01|0K context

Firefly Video supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
SEA-LION V3 Gemma2 9B
by ai-singapore|1970-01-01|0K context

SEA-LION V3 Gemma2 9B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
SEA-LION V3 Llama3.1 8B
by ai-singapore|1970-01-01|0K context

SEA-LION V3 Llama3.1 8B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
SEA-LION V3 Llama3.1 70B
by ai-singapore|1970-01-01|0K context

SEA-LION V3 Llama3.1 70B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
SEA-LION-v1-7B-IT
by ai-singapore|1970-01-01|0K context

SEA-LION-v1-7B-IT supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Jamba Mini 1.7
by ai21|1970-01-01|256K context

Jamba Mini 1.7 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jamba 1.5
by ai21|1970-01-01|256K context

Jamba 1.5 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jamba 1.5 Large@001
by ai21|1970-01-01|256K context

Jamba 1.5 Large@001 supports text input and text output with 256K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
Jamba 1.5 Mini@001
by ai21|1970-01-01|256K context

Jamba 1.5 Mini@001 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jamba Large 1.6
by ai21|1970-01-01|256K context

Jamba Large 1.6 supports text input and text output with 256K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
J2 Light
by ai21|1970-01-01|8K context

J2 Light supports text input and text output with 8K context.

$3 /M input$3 /M outputspeed —synced 2026-05-13
a
J2 Mid
by ai21|1970-01-01|8K context

J2 Mid supports text input and text output with 8K context.

$10 /M input$10 /M outputspeed —synced 2026-05-13
a
J2 Ultra
by ai21|1970-01-01|8K context

J2 Ultra supports text input and text output with 8K context.

$15 /M input$15 /M outputspeed —synced 2026-05-13
a
Jamba Large 1.7
by ai21|1970-01-01|256K context

Jamba Large 1.7 supports text input and text output with 256K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
Jamba 1.5 Mini
by ai21|1970-01-01|256K context

Jamba 1.5 Mini supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jamba Mini 1.6
by ai21|1970-01-01|256K context

Jamba Mini 1.6 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jamba 1.5 Large
by ai21|1970-01-01|256K context

Jamba 1.5 Large supports text input and text output with 256K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
Jamba 1.6 Mini
by ai21-labs|1970-01-01|0K context

Jamba 1.6 Mini supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Jamba 1.6 Large
by ai21-labs|1970-01-01|0K context

Jamba 1.6 Large supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Schnell
by aiml|1970-01-01|0K context

Schnell supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Flux Pro
by aiml|1970-01-01|0K context

Flux Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
V1.1
by aiml|1970-01-01|0K context

V1.1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
V1.1 Ultra
by aiml|1970-01-01|0K context

V1.1 Ultra supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Imagen 4.0 Ultra Generate 001
by aiml|1970-01-01|0K context

Imagen 4.0 Ultra Generate 001 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Nano Banana Pro
by aiml|1970-01-01|0K context

Nano Banana Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Text To Image
by aiml|1970-01-01|0K context

Text To Image supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Dall E 3
by aiml|1970-01-01|0K context

Dall E 3 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Flux Realism
by aiml|1970-01-01|0K context

Flux Realism supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Dall E 2
by aiml|1970-01-01|0K context

Dall E 2 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Dev
by aiml|1970-01-01|0K context

Dev supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
A
Qwen3.5-2B
by alibaba|1970-01-01|0K context

Qwen3.5-2B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3.5-0.8B
by alibaba|1970-01-01|0K context

Qwen3.5-0.8B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-VL-7B
by alibaba|1970-01-01|0K context

Qwen2.5-VL-7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3.5-122B-A10B
by alibaba|1970-01-01|262K context

Qwen3.5-122B-A10B supports text input and text output with 262K context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Qwen 3.5 Flash (hosted 35B-A3B)
by alibaba|1970-01-01|0K context

Qwen 3.5 Flash (hosted 35B-A3B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3.5-27B
by alibaba|1970-01-01|262K context

Qwen3.5-27B supports text input and text output with 262K context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Qwen3.5-9B
by alibaba|1970-01-01|262K context

Qwen3.5-9B supports text input and text output with 262K context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Qwen 3.5 Plus (hosted 397B-A17B)
by alibaba|1970-01-01|0K context

Qwen 3.5 Plus (hosted 397B-A17B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-Coder-Next
by alibaba|1970-01-01|262K context

Qwen3-Coder-Next supports text input and text output with 262K context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Qwen3-Max-Thinking
by alibaba|1970-01-01|262K context

Qwen3-Max-Thinking supports text input and text output with 262K context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Tongyi DeepResearch
by alibaba|1970-01-01|0K context

Tongyi DeepResearch supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Wan 2.5
by alibaba|1970-01-01|0K context

Wan 2.5 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-Omni-Flash
by alibaba|1970-01-01|0K context

Qwen3-Omni-Flash supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-Omni-30B-A3B
by alibaba|1970-01-01|0K context

Qwen3-Omni-30B-A3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
AgentFounder-30B
by alibaba|1970-01-01|0K context

AgentFounder-30B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-Next-80B-A3B
by alibaba|1970-01-01|0K context

Qwen3-Next-80B-A3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Wan 2.2 14B S2V
by alibaba|1970-01-01|0K context

Wan 2.2 14B S2V supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen Image Edit
by alibaba|1970-01-01|0K context

Qwen Image Edit supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Ovis2.5 9B
by alibaba|1970-01-01|0K context

Ovis2.5 9B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Ovis2.5 2B
by alibaba|1970-01-01|0K context

Ovis2.5 2B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen Image
by alibaba|1970-01-01|0K context

Qwen Image supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Wan 2.2 14B T2V
by alibaba|1970-01-01|0K context

Wan 2.2 14B T2V supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Wan 2.2 14B I2V
by alibaba|1970-01-01|0K context

Wan 2.2 14B I2V supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-235B-A22B-Thinking (Jul 2025)
by alibaba|1970-01-01|0K context

Qwen3-235B-A22B-Thinking (Jul 2025) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-235B-A22B (Jul 2025)
by alibaba|1970-01-01|0K context

Qwen3-235B-A22B (Jul 2025) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-Coder-480B-A35B
by alibaba|1970-01-01|0K context

Qwen3-Coder-480B-A35B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3 Embedding
by alibaba|1970-01-01|0K context

Qwen3 Embedding supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3 Reranker
by alibaba|1970-01-01|0K context

Qwen3 Reranker supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen3-1.7B
by alibaba|1970-01-01|0K context

Qwen3-1.7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
QVQ-Max
by alibaba|1970-01-01|0K context

QVQ-Max supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Omni 7B
by alibaba|1970-01-01|0K context

Qwen2.5-Omni 7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Omni 3B
by alibaba|1970-01-01|0K context

Qwen2.5-Omni 3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Wan 2.1 14B I2V
by alibaba|1970-01-01|0K context

Wan 2.1 14B I2V supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-VL-72B
by alibaba|1970-01-01|0K context

Qwen2.5-VL-72B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-VL-3B
by alibaba|1970-01-01|0K context

Qwen2.5-VL-3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Animate Anyone 2
by alibaba|1970-01-01|0K context

Animate Anyone 2 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Max
by alibaba|1970-01-01|0K context

Qwen2.5-Max supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
gte-modernbert
by alibaba|1970-01-01|0K context

gte-modernbert supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
QVQ
by alibaba|1970-01-01|0K context

QVQ supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Ovis1.6-Gemma2-27B
by alibaba|1970-01-01|0K context

Ovis1.6-Gemma2-27B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Turbo
by alibaba|1970-01-01|0K context

Qwen2.5-Turbo supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Coder (32B)
by alibaba|1970-01-01|0K context

Qwen2.5-Coder (32B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Marco-o1
by alibaba|1970-01-01|0K context

Marco-o1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-72B
by alibaba|1970-01-01|0K context

Qwen2.5-72B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5 Instruct (7B)
by alibaba|1970-01-01|0K context

Qwen2.5 Instruct (7B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5 Instruct (72B)
by alibaba|1970-01-01|0K context

Qwen2.5 Instruct (72B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-3B
by alibaba|1970-01-01|0K context

Qwen2.5-3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-7B
by alibaba|1970-01-01|0K context

Qwen2.5-7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-1.5B
by alibaba|1970-01-01|0K context

Qwen2.5-1.5B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-14B
by alibaba|1970-01-01|0K context

Qwen2.5-14B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Math-7B-Base
by alibaba|1970-01-01|0K context

Qwen2.5-Math-7B-Base supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5 Instruct (32B)
by alibaba|1970-01-01|0K context

Qwen2.5 Instruct (32B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Math-1.5B
by alibaba|1970-01-01|0K context

Qwen2.5-Math-1.5B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2-VL-72B
by alibaba|1970-01-01|0K context

Qwen2-VL-72B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2-VL-2B
by alibaba|1970-01-01|0K context

Qwen2-VL-2B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2-VL-7B
by alibaba|1970-01-01|0K context

Qwen2-VL-7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-Coder (1.5B)
by alibaba|1970-01-01|0K context

Qwen2.5-Coder (1.5B) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Qwen2.5-32B
by alibaba|1970-01-01|0K context

Qwen2.5-32B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Ovis1.6-Gemma2-9B
by alibaba|1970-01-01|0K context

Ovis1.6-Gemma2-9B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Xunguang
by alibaba-damo-academy|1970-01-01|0K context

Xunguang supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Alibaba-NLP (mGTE)
by alibaba-hong-kong-polytechnic-university|1970-01-01|0K context

Alibaba-NLP (mGTE) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Olmo 3
by allen-institute-for-ai|1970-01-01|0K context

Olmo 3 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Atlantes
by allen-institute-for-ai|1970-01-01|0K context

Atlantes supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
CodeScientist
by allen-institute-for-ai|1970-01-01|0K context

CodeScientist supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
OLMo 2 32B
by allen-institute-for-ai|1970-01-01|0K context

OLMo 2 32B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
MolmoAct-7B-D
by allen-institute-for-ai-university-of-washington|1970-01-01|0K context

MolmoAct-7B-D supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Tulu 3 405B
by allen-institute-for-ai-university-of-washington|1970-01-01|0K context

Tulu 3 405B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Tulu 3 (Tülu 3) 70B
by allen-institute-for-ai-university-of-washington|1970-01-01|0K context

Tulu 3 (Tülu 3) 70B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Tulu 3 8B
by allen-institute-for-ai-university-of-washington|1970-01-01|0K context

Tulu 3 8B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Molmo 72B
by allen-institute-for-ai-university-of-washington|1970-01-01|0K context

Molmo 72B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Olmo 3 32B Instruct
by allen-institute-for-ai-university-of-washington-carnegie-mellon-university-cmu-stanford-university-mila-quebec-ai-originally-montreal-institute-for-learning-algorithms-university-of-montreal-universit-de-montr-al-princeton-university-massachusetts-institute-of-technology-mit-university-of-maryland|1970-01-01|0K context

Olmo 3 32B Instruct supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Olmo 3.1 32B Think
by allen-institute-for-ai-university-of-washington-carnegie-mellon-university-cmu-stanford-university-mila-quebec-ai-originally-montreal-institute-for-learning-algorithms-university-of-montreal-universit-de-montr-al-princeton-university-massachusetts-institute-of-technology-mit-university-of-maryland|1970-01-01|0K context

Olmo 3.1 32B Think supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
OLMo 2 Furious 13B
by allen-institute-for-ai-university-of-washington-new-york-university-nyu|1970-01-01|0K context

OLMo 2 Furious 13B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
OLMo 2 Furious 7B
by allen-institute-for-ai-university-of-washington-new-york-university-nyu|1970-01-01|0K context

OLMo 2 Furious 7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Nova 2 Pro (Preview)
by amazon|1970-01-01|0K context

Nova 2 Pro (Preview) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Premier
by amazon|1970-01-01|0K context

Amazon Nova Premier supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Sonic
by amazon|1970-01-01|0K context

Amazon Nova Sonic supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Reel
by amazon|1970-01-01|0K context

Amazon Nova Reel supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Act
by amazon|1970-01-01|0K context

Amazon Nova Act supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Pro
by amazon|1970-01-01|0K context

Amazon Nova Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Lite
by amazon|1970-01-01|0K context

Amazon Nova Lite supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Micro
by amazon|1970-01-01|0K context

Amazon Nova Micro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Amazon Nova Canvas
by amazon|1970-01-01|0K context

Amazon Nova Canvas supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Nova Micro V1
by amazon_nova|1970-01-01|128K context

Nova Micro V1 supports text input and text output with 128K context, suited for cheap batch.

$0.035 /M input$0.14 /M outputspeed —synced 2026-05-13
Cheap batch
a
Nova Lite V1
by amazon_nova|1970-01-01|300K context

Nova Lite V1 supports text input and text output with 300K context, suited for long context, cheap batch.

$0.06 /M input$0.24 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Nova Premier V1
by amazon_nova|1970-01-01|1M context

Nova Premier V1 supports text input and text output with 1M context, suited for long context.

$2.5 /M input$12.5 /M outputspeed —synced 2026-05-13
Long context
a
Nova Pro V1
by amazon_nova|1970-01-01|300K context

Nova Pro V1 supports text input and text output with 300K context, suited for long context.

$0.8 /M input$3.2 /M outputspeed —synced 2026-05-13
Long context
a
Ring-mini-linear-2.0
by ant-group|1970-01-01|0K context

Ring-mini-linear-2.0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ring-flash-linear-2.0
by ant-group|1970-01-01|0K context

Ring-flash-linear-2.0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ring-1T
by ant-group|1970-01-01|0K context

Ring-1T supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ling-1T
by ant-group|1970-01-01|0K context

Ling-1T supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ling-mini-base-2.0-20T
by ant-group|1970-01-01|0K context

Ling-mini-base-2.0-20T supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ling-flash-base-2.0-20T
by ant-group|1970-01-01|0K context

Ling-flash-base-2.0-20T supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Agentar-Fin-R1 32B
by ant-group|1970-01-01|0K context

Agentar-Fin-R1 32B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Agentar-Fin-R1 8B
by ant-group|1970-01-01|0K context

Agentar-Fin-R1 8B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Finix-P1-32B
by ant-group|1970-01-01|0K context

Finix-P1-32B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ling-lite-1.5 ("Bailing")
by ant-group|1970-01-01|0K context

Ling-lite-1.5 ("Bailing") supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ling-Plus ("Bailing")
by ant-group|1970-01-01|0K context

Ling-Plus ("Bailing") supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Bailing-Pro-20250225
by ant-group|1970-01-01|0K context

Bailing-Pro-20250225 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
bailing-pro-1120
by ant-group|1970-01-01|0K context

bailing-pro-1120 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Odyssey 102B
by anthrogen|1970-01-01|0K context

Odyssey 102B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Odyssey 12B
by anthrogen|1970-01-01|0K context

Odyssey 12B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Odyssey 1.2B
by anthrogen|1970-01-01|0K context

Odyssey 1.2B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
A
Anthropic: Claude Opus 4.6 (Fast)
by anthropic|1970-01-01|1M context

Anthropic: Claude Opus 4.6 (Fast) supports text input and text output with 1M context, suited for long context.

$30 /M input$150 /M outputspeed —synced 2026-05-12
Long context
A
Anthropic: Claude Opus 4.7 (Fast)
by anthropic|1970-01-01|1M context

Anthropic: Claude Opus 4.7 (Fast) supports text input and text output with 1M context, suited for long context.

$30 /M input$150 /M outputspeed —synced 2026-05-13
Long context
A
Claude 4 Opus 20250514
by anthropic|1970-01-01|200K context

Claude 4 Opus 20250514 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
A
Anthropic: Claude Opus 4
by anthropic|1970-01-01|200K context

Anthropic: Claude Opus 4 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-12
Long context
A
Anthropic: Claude Sonnet 4
by anthropic|1970-01-01|1M context

Anthropic: Claude Sonnet 4 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-12
Long context
A
Anthropic: Claude 3.5 Haiku
by anthropic|1970-01-01|200K context

Anthropic: Claude 3.5 Haiku supports text input and text output with 200K context, suited for long context.

$0.8 /M input$4 /M outputspeed —synced 2026-05-13
Long context
A
Anthropic: Claude 3 Haiku
by anthropic|1970-01-01|200K context

Anthropic: Claude 3 Haiku supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-12
Long contextCheap batch
A
Claude Haiku 4 5 20251001
by anthropic|1970-01-01|200K context

Claude Haiku 4 5 20251001 supports text input and text output with 200K context, suited for long context.

$1 /M input$5 /M outputspeed —synced 2026-05-13
Long context
A
Claude 3 7 Sonnet 20250219
by anthropic|1970-01-01|200K context

Claude 3 7 Sonnet 20250219 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
A
Claude 3 Haiku 20240307
by anthropic|1970-01-01|200K context

Claude 3 Haiku 20240307 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
A
Claude 3 Opus 20240229
by anthropic|1970-01-01|200K context

Claude 3 Opus 20240229 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
A
Claude 4 Sonnet 20250514
by anthropic|1970-01-01|1M context

Claude 4 Sonnet 20250514 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
A
Claude Sonnet 4 5 20250929
by anthropic|1970-01-01|200K context

Claude Sonnet 4 5 20250929 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
A
Claude Opus 4 1 20250805
by anthropic|1970-01-01|200K context

Claude Opus 4 1 20250805 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
A
Claude Opus 4 5 20251101
by anthropic|1970-01-01|200K context

Claude Opus 4 5 20251101 supports text input and text output with 200K context, suited for long context.

$5 /M input$25 /M outputspeed —synced 2026-05-13
Long context
A
Claude Opus 4 6 20260205
by anthropic|1970-01-01|1M context

Claude Opus 4 6 20260205 supports text input and text output with 1M context, suited for long context.

$5 /M input$25 /M outputspeed —synced 2026-05-13
Long context
A
Claude Opus 4 7 20260416
by anthropic|1970-01-01|1M context

Claude Opus 4 7 20260416 supports text input and text output with 1M context, suited for long context.

$5 /M input$25 /M outputspeed —synced 2026-05-13
Long context
A
Claude Sonnet 4 20250514
by anthropic|1970-01-01|1M context

Claude Sonnet 4 20250514 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
A
Claude Opus 4 20250514
by anthropic|1970-01-01|200K context

Claude Opus 4 20250514 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
A
Claude Gov
by anthropic|1970-01-01|0K context

Claude Gov supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Zephyr 7b Beta
by anyscale|1970-01-01|33K context

Zephyr 7b Beta supports text input and text output with 33K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
CodeLlama 34b Instruct Hf
by anyscale|1970-01-01|4K context

CodeLlama 34b Instruct Hf supports text input and text output with 4K context.

$1 /M input$1 /M outputspeed —synced 2026-05-13
a
CodeLlama 70b Instruct Hf
by anyscale|1970-01-01|4K context

CodeLlama 70b Instruct Hf supports text input and text output with 4K context.

$1 /M input$1 /M outputspeed —synced 2026-05-13
a
Llama 2 13b Chat Hf
by anyscale|1970-01-01|4K context

Llama 2 13b Chat Hf supports text input and text output with 4K context, suited for cheap batch.

$0.25 /M input$0.25 /M outputspeed —synced 2026-05-13
Cheap batch
a
Llama 2 7b Chat Hf
by anyscale|1970-01-01|4K context

Llama 2 7b Chat Hf supports text input and text output with 4K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta Llama 3 70B Instruct
by anyscale|1970-01-01|8K context

Meta Llama 3 70B Instruct supports text input and text output with 8K context.

$1 /M input$1 /M outputspeed —synced 2026-05-12
a
Meta Llama 3 8B Instruct
by anyscale|1970-01-01|8K context

Meta Llama 3 8B Instruct supports text input and text output with 8K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-12
Cheap batch
a
Mixtral 8x22B Instruct V0.1
by anyscale|1970-01-01|66K context

Mixtral 8x22B Instruct V0.1 supports text input and text output with 66K context.

$0.9 /M input$0.9 /M outputspeed —synced 2026-05-13
a
Llama 2 70b Chat Hf
by anyscale|1970-01-01|4K context

Llama 2 70b Chat Hf supports text input and text output with 4K context.

$1 /M input$1 /M outputspeed —synced 2026-05-13
a
Mistral 7B Instruct V0.1
by anyscale|1970-01-01|16K context

Mistral 7B Instruct V0.1 supports text input and text output with 16K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gemma 7b It
by anyscale|1970-01-01|8K context

Gemma 7b It supports text input and text output with 8K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mixtral 8x7B Instruct V0.1
by anyscale|1970-01-01|33K context

Mixtral 8x7B Instruct V0.1 supports text input and text output with 33K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
SimpleFold
by apple|1970-01-01|0K context

SimpleFold supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Evo 2 40B
by arc-institute-stanford-university-nvidia-liquid-university-of-california-uc-berkeley-goodfire-columbia-university-university-of-california-san-francisco|1970-01-01|0K context

Evo 2 40B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Evo 2 7B
by arc-institute-stanford-university-nvidia-liquid-university-of-california-uc-berkeley-goodfire-columbia-university-university-of-california-san-francisco|1970-01-01|0K context

Evo 2 7B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Best
by assemblyai|1970-01-01|0K context

Best supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Nano
by assemblyai|1970-01-01|0K context

Nano supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Universal-2-TF
by assemblyai|1970-01-01|0K context

Universal-2-TF supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
PepINVENT
by astrazeneca-chalmers-university-of-technology|1970-01-01|0K context

PepINVENT supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Ai21.Jamba 1 5 Large V1:0
by aws|1970-01-01|256K context

Ai21.Jamba 1 5 Large V1:0 supports text input and text output with 256K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
Stability.Stable Diffusion Xl V0
by aws|1970-01-01|0K context

Stability.Stable Diffusion Xl V0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Ai21.Jamba 1 5 Mini V1:0
by aws|1970-01-01|256K context

Ai21.Jamba 1 5 Mini V1:0 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Ai21.Jamba Instruct V1:0
by aws|1970-01-01|70K context

Ai21.Jamba Instruct V1:0 supports text input and text output with 70K context, suited for cheap batch.

$0.5 /M input$0.7 /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Amazon.Nova Canvas V1:0
by aws|1970-01-01|3K context

Us.Amazon.Nova Canvas V1:0 supports text input and text output with 3K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Anthropic.Claude 3 5 Sonnet 20240620 V1:0
by aws|1970-01-01|1M context

Anthropic.Claude 3 5 Sonnet 20240620 V1:0 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Amazon.Nova 2 Multimodal Embeddings V1:0
by aws|1970-01-01|8K context

Amazon.Nova 2 Multimodal Embeddings V1:0 supports text input and text output with 8K context, suited for cheap batch.

$0.135 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Amazon.Titan Embed Text V1
by aws|1970-01-01|8K context

Amazon.Titan Embed Text V1 supports text input and text output with 8K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Amazon.Titan Image Generator V1
by aws|1970-01-01|0K context

Amazon.Titan Image Generator V1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Amazon.Titan Image Generator V2
by aws|1970-01-01|0K context

Amazon.Titan Image Generator V2 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Amazon.Titan Image Generator V2:0
by aws|1970-01-01|0K context

Amazon.Titan Image Generator V2:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Twelvelabs.Marengo Embed 2 7 V1:0
by aws|1970-01-01|0K context

Us.Twelvelabs.Marengo Embed 2 7 V1:0 supports text input and text output with 0K context.

$70 /M inputFree /M outputspeed —synced 2026-05-13
a
Eu.Twelvelabs.Marengo Embed 2 7 V1:0
by aws|1970-01-01|0K context

Eu.Twelvelabs.Marengo Embed 2 7 V1:0 supports text input and text output with 0K context.

$70 /M inputFree /M outputspeed —synced 2026-05-13
a
Us.Twelvelabs.Pegasus 1 2 V1:0
by aws|1970-01-01|0K context

Us.Twelvelabs.Pegasus 1 2 V1:0 supports text input and text output with 0K context.

Free /M input$7.5 /M outputspeed —synced 2026-05-13
a
Eu.Twelvelabs.Pegasus 1 2 V1:0
by aws|1970-01-01|0K context

Eu.Twelvelabs.Pegasus 1 2 V1:0 supports text input and text output with 0K context.

Free /M input$7.5 /M outputspeed —synced 2026-05-13
a
Amazon.Titan Text Express V1
by aws|1970-01-01|42K context

Amazon.Titan Text Express V1 supports text input and text output with 42K context.

$1.3 /M input$1.7 /M outputspeed —synced 2026-05-13
a
Amazon.Titan Text Lite V1
by aws|1970-01-01|42K context

Amazon.Titan Text Lite V1 supports text input and text output with 42K context, suited for cheap batch.

$0.3 /M input$0.4 /M outputspeed —synced 2026-05-13
Cheap batch
a
Amazon.Titan Text Premier V1:0
by aws|1970-01-01|42K context

Amazon.Titan Text Premier V1:0 supports text input and text output with 42K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Anthropic.Claude 3 5 Haiku 20241022 V1:0
by aws|1970-01-01|200K context

Anthropic.Claude 3 5 Haiku 20241022 V1:0 supports text input and text output with 200K context, suited for long context.

$0.8 /M input$4 /M outputspeed —synced 2026-05-13
Long context
a
Anthropic.Claude 3 5 Sonnet 20241022 V2:0
by aws|1970-01-01|1M context

Anthropic.Claude 3 5 Sonnet 20241022 V2:0 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Anthropic.Claude 3 7 Sonnet 20240620 V1:0
by aws|1970-01-01|200K context

Anthropic.Claude 3 7 Sonnet 20240620 V1:0 supports text input and text output with 200K context, suited for long context.

$3.6 /M input$18 /M outputspeed —synced 2026-05-13
Long context
a
Anthropic.Claude 3 Haiku 20240307 V1:0
by aws|1970-01-01|200K context

Anthropic.Claude 3 Haiku 20240307 V1:0 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Anthropic.Claude 3 Opus 20240229 V1:0
by aws|1970-01-01|200K context

Anthropic.Claude 3 Opus 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
a
Anthropic.Claude 3 Sonnet 20240229 V1:0
by aws|1970-01-01|200K context

Anthropic.Claude 3 Sonnet 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Anthropic.Claude Instant V1
by aws|1970-01-01|100K context

Anthropic.Claude Instant V1 supports text input and text output with 100K context.

$0.8 /M input$2.4 /M outputspeed —synced 2026-05-13
a
Amazon.Titan Embed Image V1
by aws|1970-01-01|0K context

Amazon.Titan Embed Image V1 supports text input and text output with 0K context.

$0.8 /M inputFree /M outputspeed —synced 2026-05-13
a
Anthropic.Claude Mythos Preview
by aws|1970-01-01|1M context

Anthropic.Claude Mythos Preview supports text input and text output with 1M context, suited for long context, cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Long contextCheap batch
a

Apac.Anthropic.Claude 3 5 Sonnet 20241022 V2:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Apac.Anthropic.Claude 3 Haiku 20240307 V1:0
by aws|1970-01-01|200K context

Apac.Anthropic.Claude 3 Haiku 20240307 V1:0 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Apac.Anthropic.Claude 3 Sonnet 20240229 V1:0
by aws|1970-01-01|200K context

Apac.Anthropic.Claude 3 Sonnet 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Stability.Stable Creative Upscale V1:0
by aws|1970-01-01|0K context

Stability.Stable Creative Upscale V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Anthropic.Claude V1
by aws|1970-01-01|100K context

Anthropic.Claude V1 supports text input and text output with 100K context.

$8 /M input$24 /M outputspeed —synced 2026-05-13
a
Cohere.Command R V1:0
by aws|1970-01-01|128K context

Cohere.Command R V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Anthropic.Claude 3 5 Sonnet 20240620 V1:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 5 Sonnet 20240620 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Amazon.Rerank V1:0
by aws|1970-01-01|32K context

Amazon.Rerank V1:0 supports text input and text output with 32K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama2 13b Chat V1
by aws|1970-01-01|4K context

Meta.Llama2 13b Chat V1 supports text input and text output with 4K context.

$0.75 /M input$1 /M outputspeed —synced 2026-05-13
a
Meta.Llama3 8b Instruct V1:0
by aws|1970-01-01|8K context

Meta.Llama3 8b Instruct V1:0 supports text input and text output with 8K context, suited for cheap batch.

$0.36 /M input$0.72 /M outputspeed —synced 2026-05-13
Cheap batch
a
Deepseek.V3.2
by aws|1970-01-01|164K context

Deepseek.V3.2 supports text input and text output with 164K context.

$0.74 /M input$2.22 /M outputspeed —synced 2026-05-12
a
Moonshotai.Kimi K2.5
by aws|1970-01-01|262K context

Moonshotai.Kimi K2.5 supports text input and text output with 262K context, suited for long context.

$0.72 /M input$3.6 /M outputspeed —synced 2026-05-13
Long context
a
Claude Sonnet 4 5 20250929 V1:0
by aws|1970-01-01|200K context

Claude Sonnet 4 5 20250929 V1:0 supports text input and text output with 200K context, suited for long context.

$3.3 /M input$16.5 /M outputspeed —synced 2026-05-13
Long context
a
Meta.Llama3 70b Instruct V1:0
by aws|1970-01-01|8K context

Meta.Llama3 70b Instruct V1:0 supports text input and text output with 8K context.

$3.18 /M input$4.2 /M outputspeed —synced 2026-05-13
a
Us.Anthropic.Claude 3 5 Haiku 20241022 V1:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 5 Haiku 20241022 V1:0 supports text input and text output with 200K context, suited for long context.

$0.8 /M input$4 /M outputspeed —synced 2026-05-13
Long context
a
Mistral.Mistral 7b Instruct V0:2
by aws|1970-01-01|32K context

Mistral.Mistral 7b Instruct V0:2 supports text input and text output with 32K context, suited for cheap batch.

$0.2 /M input$0.26 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral.Mistral Large 2402 V1:0
by aws|1970-01-01|32K context

Mistral.Mistral Large 2402 V1:0 supports text input and text output with 32K context.

$10.4 /M input$31.2 /M outputspeed —synced 2026-05-13
a
Cohere.Command R Plus V1:0
by aws|1970-01-01|128K context

Cohere.Command R Plus V1:0 supports text input and text output with 128K context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
a
Cohere.Embed English V3
by aws|1970-01-01|1K context

Cohere.Embed English V3 supports text input and text output with 1K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Cohere.Embed Multilingual V3
by aws|1970-01-01|1K context

Cohere.Embed Multilingual V3 supports text input and text output with 1K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Cohere.Rerank V3 5:0
by aws|1970-01-01|32K context

Cohere.Rerank V3 5:0 supports text input and text output with 32K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Eu.Anthropic.Claude 3 5 Haiku 20241022 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 5 Haiku 20241022 V1:0 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Eu.Anthropic.Claude 3 5 Sonnet 20240620 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 5 Sonnet 20240620 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Eu.Anthropic.Claude 3 5 Sonnet 20241022 V2:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 5 Sonnet 20241022 V2:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Eu.Anthropic.Claude 3 7 Sonnet 20250219 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 7 Sonnet 20250219 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Eu.Meta.Llama3 2 1b Instruct V1:0
by aws|1970-01-01|128K context

Eu.Meta.Llama3 2 1b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.13 /M input$0.13 /M outputspeed —synced 2026-05-13
Cheap batch
a
Eu.Meta.Llama3 2 3b Instruct V1:0
by aws|1970-01-01|128K context

Eu.Meta.Llama3 2 3b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.19 /M input$0.19 /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Diffusion Xl V1
by aws|1970-01-01|0K context

Stability.Stable Diffusion Xl V1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama2 70b Chat V1
by aws|1970-01-01|4K context

Meta.Llama2 70b Chat V1 supports text input and text output with 4K context.

$1.95 /M input$2.56 /M outputspeed —synced 2026-05-13
a
Meta.Llama3 1 70b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 1 70b Instruct V1:0 supports text input and text output with 128K context.

$0.99 /M input$0.99 /M outputspeed —synced 2026-05-13
a
Meta.Llama3 1 8b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 1 8b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.22 /M input$0.22 /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama3 2 11b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 2 11b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.35 /M input$0.35 /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama3 2 1b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 2 1b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.1 /M input$0.1 /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama3 2 3b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 2 3b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Meta.Llama3 2 90b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 2 90b Instruct V1:0 supports text input and text output with 128K context.

$2 /M input$2 /M outputspeed —synced 2026-05-13
a
Amazon.Nova Canvas V1:0
by aws|1970-01-01|3K context

Amazon.Nova Canvas V1:0 supports text input and text output with 3K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Ai21.J2 Mid V1
by aws|1970-01-01|8K context

Ai21.J2 Mid V1 supports text input and text output with 8K context.

$12.5 /M input$12.5 /M outputspeed —synced 2026-05-13
a
Amazon.Titan Embed Text V2:0
by aws|1970-01-01|8K context

Amazon.Titan Embed Text V2:0 supports text input and text output with 8K context, suited for cheap batch.

$0.2 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Twelvelabs.Marengo Embed 2 7 V1:0
by aws|1970-01-01|0K context

Twelvelabs.Marengo Embed 2 7 V1:0 supports text input and text output with 0K context.

$70 /M inputFree /M outputspeed —synced 2026-05-13
a
Us.Anthropic.Claude 3 Opus 20240229 V1:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 Opus 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
a
Mistral.Mistral Small 2402 V1:0
by aws|1970-01-01|32K context

Mistral.Mistral Small 2402 V1:0 supports text input and text output with 32K context.

$1 /M input$3 /M outputspeed —synced 2026-05-13
a
Cohere.Command Text V14
by aws|1970-01-01|4K context

Cohere.Command Text V14 supports text input and text output with 4K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Eu.Anthropic.Claude 3 Haiku 20240307 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 Haiku 20240307 V1:0 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Eu.Anthropic.Claude 3 Opus 20240229 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 Opus 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
a
Eu.Anthropic.Claude 3 Sonnet 20240229 V1:0
by aws|1970-01-01|200K context

Eu.Anthropic.Claude 3 Sonnet 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Us.Anthropic.Claude 3 Haiku 20240307 V1:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 Haiku 20240307 V1:0 supports text input and text output with 200K context, suited for long context, cheap batch.

$0.25 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Mistral.Mistral Large 2407 V1:0
by aws|1970-01-01|128K context

Mistral.Mistral Large 2407 V1:0 supports text input and text output with 128K context.

$3 /M input$9 /M outputspeed —synced 2026-05-13
a
Us.Anthropic.Claude 3 5 Sonnet 20241022 V2:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 5 Sonnet 20241022 V2:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Us.Anthropic.Claude 3 Sonnet 20240229 V1:0
by aws|1970-01-01|200K context

Us.Anthropic.Claude 3 Sonnet 20240229 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Stability.Stable Outpaint V1:0
by aws|1970-01-01|0K context

Stability.Stable Outpaint V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Ultra V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Ultra V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Meta.Llama3 2 90b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 2 90b Instruct V1:0 supports text input and text output with 128K context.

$2 /M input$2 /M outputspeed —synced 2026-05-13
a
Stability.Sd3 Large V1:0
by aws|1970-01-01|0K context

Stability.Sd3 Large V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a

Stability.Stable Image Remove Background V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Style Guide V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Style Guide V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Meta.Llama3 2 3b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 2 3b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Twelvelabs.Pegasus 1 2 V1:0
by aws|1970-01-01|0K context

Twelvelabs.Pegasus 1 2 V1:0 supports text input and text output with 0K context.

Free /M input$7.5 /M outputspeed —synced 2026-05-13
a
Stability.Stable Conservative Upscale V1:0
by aws|1970-01-01|0K context

Stability.Stable Conservative Upscale V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Core V1:1
by aws|1970-01-01|0K context

Stability.Stable Image Core V1:1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Meta.Llama3 1 8b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 1 8b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.22 /M input$0.22 /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Erase Object V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Erase Object V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Search Replace V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Search Replace V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Control Sketch V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Control Sketch V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Style Transfer V1:0
by aws|1970-01-01|0K context

Stability.Stable Style Transfer V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Sd3 5 Large V1:0
by aws|1970-01-01|0K context

Stability.Sd3 5 Large V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a

Stability.Stable Image Control Structure V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Search Recolor V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Search Recolor V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Meta.Llama3 2 11b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 2 11b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.35 /M input$0.35 /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Inpaint V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Inpaint V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Us.Meta.Llama3 1 70b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 1 70b Instruct V1:0 supports text input and text output with 128K context.

$0.99 /M input$0.99 /M outputspeed —synced 2026-05-13
a
Stability.Stable Image Core V1:0
by aws|1970-01-01|0K context

Stability.Stable Image Core V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Fast Upscale V1:0
by aws|1970-01-01|0K context

Stability.Stable Fast Upscale V1:0 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Stability.Stable Image Ultra V1:1
by aws|1970-01-01|0K context

Stability.Stable Image Ultra V1:1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Ai21.J2 Ultra V1
by aws|1970-01-01|8K context

Ai21.J2 Ultra V1 supports text input and text output with 8K context.

$18.8 /M input$18.8 /M outputspeed —synced 2026-05-13
a
Us.Meta.Llama3 1 405b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 1 405b Instruct V1:0 supports text input and text output with 128K context.

$5.32 /M input$16 /M outputspeed —synced 2026-05-13
a
Us.Meta.Llama3 2 1b Instruct V1:0
by aws|1970-01-01|128K context

Us.Meta.Llama3 2 1b Instruct V1:0 supports text input and text output with 128K context, suited for cheap batch.

$0.1 /M input$0.1 /M outputspeed —synced 2026-05-13
Cheap batch
a

Apac.Anthropic.Claude 3 5 Sonnet 20240620 V1:0 supports text input and text output with 200K context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Mistral.Mixtral 8x7b Instruct V0:1
by aws|1970-01-01|32K context

Mistral.Mixtral 8x7b Instruct V0:1 supports text input and text output with 32K context.

$0.59 /M input$0.91 /M outputspeed —synced 2026-05-13
a
Cohere.Embed V4:0
by aws|1970-01-01|128K context

Cohere.Embed V4:0 supports text input and text output with 128K context, suited for cheap batch.

$0.12 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Anthropic.Claude V2:1
by aws|1970-01-01|100K context

Anthropic.Claude V2:1 supports text input and text output with 100K context.

$8 /M input$24 /M outputspeed —synced 2026-05-13
a
Cohere.Command Light Text V14
by aws|1970-01-01|4K context

Cohere.Command Light Text V14 supports text input and text output with 4K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Zai.Glm 5
by aws|1970-01-01|200K context

Zai.Glm 5 supports text input and text output with 200K context, suited for long context.

$1 /M input$3.2 /M outputspeed —synced 2026-05-13
Long context
a
Meta.Llama3 1 405b Instruct V1:0
by aws|1970-01-01|128K context

Meta.Llama3 1 405b Instruct V1:0 supports text input and text output with 128K context.

$5.32 /M input$16 /M outputspeed —synced 2026-05-13
a
Generative
by aws_polly|1970-01-01|0K context

Generative supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Long Form
by aws_polly|1970-01-01|0K context

Long Form supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Standard
by aws_polly|1970-01-01|0K context

Standard supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Neural
by aws_polly|1970-01-01|0K context

Neural supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Ada
by azure|1970-01-01|8K context

Ada supports text input and text output with 8K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt Realtime Mini 2025 10 06
by azure|1970-01-01|128K context

Gpt Realtime Mini 2025 10 06 supports text input and text output with 128K context.

$0.6 /M input$2.4 /M outputspeed —synced 2026-05-13
a
Computer Use Preview
by azure|1970-01-01|8K context

Computer Use Preview supports text input and text output with 8K context.

$3 /M input$12 /M outputspeed —synced 2026-05-13
a
Gpt 4o 2024 08 06
by azure|1970-01-01|128K context

Gpt 4o 2024 08 06 supports text input and text output with 128K context.

$2.75 /M input$11 /M outputspeed —synced 2026-05-13
a
Gpt 4o Mini 2024 07 18
by azure|1970-01-01|128K context

Gpt 4o Mini 2024 07 18 supports text input and text output with 128K context, suited for cheap batch.

$0.165 /M input$0.66 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 4o Mini Realtime Preview 2024 12 17
by azure|1970-01-01|128K context

Gpt 4o Mini Realtime Preview 2024 12 17 supports text input and text output with 128K context.

$0.66 /M input$2.64 /M outputspeed —synced 2026-05-13
a
Gpt 4o Realtime Preview 2024 10 01
by azure|1970-01-01|128K context

Gpt 4o Realtime Preview 2024 10 01 supports text input and text output with 128K context.

$5.5 /M input$22 /M outputspeed —synced 2026-05-13
a
Gpt 4o Realtime Preview 2024 12 17
by azure|1970-01-01|128K context

Gpt 4o Realtime Preview 2024 12 17 supports text input and text output with 128K context.

$5.5 /M input$22 /M outputspeed —synced 2026-05-13
a
Gpt 5 2025 08 07
by azure|1970-01-01|272K context

Gpt 5 2025 08 07 supports text input and text output with 272K context, suited for long context.

$1.375 /M input$11 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5 Mini 2025 08 07
by azure|1970-01-01|272K context

Gpt 5 Mini 2025 08 07 supports text input and text output with 272K context, suited for long context.

$0.275 /M input$2.2 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.1
by azure|1970-01-01|410K context

Gpt 5.1 supports text input and text output with 410K context, suited for long context.

$1.38 /M input$11 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.1 Chat
by azure|1970-01-01|128K context

Gpt 5.1 Chat supports text input and text output with 128K context.

$1.38 /M input$11 /M outputspeed —synced 2026-05-13
a
Gpt 5.1 Codex
by azure|1970-01-01|400K context

Gpt 5.1 Codex supports text input and text output with 400K context, suited for long context.

$1.38 /M input$11 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.1 Codex Mini
by azure|1970-01-01|400K context

Gpt 5.1 Codex Mini supports text input and text output with 400K context, suited for long context.

$0.275 /M input$2.2 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5 Nano 2025 08 07
by azure|1970-01-01|272K context

Gpt 5 Nano 2025 08 07 supports text input and text output with 272K context, suited for long context, cheap batch.

$0.055 /M input$0.44 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
O1 2024 12 17
by azure|1970-01-01|200K context

O1 2024 12 17 supports text input and text output with 200K context, suited for long context.

$16.5 /M input$66 /M outputspeed —synced 2026-05-13
Long context
a
O1 Mini 2024 09 12
by azure|1970-01-01|128K context

O1 Mini 2024 09 12 supports text input and text output with 128K context.

$1.21 /M input$4.84 /M outputspeed —synced 2026-05-13
a
O1 Preview 2024 09 12
by azure|1970-01-01|128K context

O1 Preview 2024 09 12 supports text input and text output with 128K context.

$16.5 /M input$66 /M outputspeed —synced 2026-05-13
a
O3 Mini 2025 01 31
by azure|1970-01-01|200K context

O3 Mini 2025 01 31 supports text input and text output with 200K context, suited for long context.

$1.21 /M input$4.84 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 3.5 Turbo
by azure|1970-01-01|16K context

Gpt 3.5 Turbo supports text input and text output with 16K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 3.5 Turbo 0125
by azure|1970-01-01|16K context

Gpt 3.5 Turbo 0125 supports text input and text output with 16K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 5.2 Chat 2025 12 11
by azure|1970-01-01|128K context

Gpt 5.2 Chat 2025 12 11 supports text input and text output with 128K context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-13
a
Gpt 3.5 Turbo Instruct 0914
by azure|1970-01-01|8K context

Gpt 3.5 Turbo Instruct 0914 supports text input and text output with 8K context.

$1.5 /M input$2 /M outputspeed —synced 2026-05-13
a
Gpt 35 Turbo
by azure|1970-01-01|4K context

Gpt 35 Turbo supports text input and text output with 4K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 35 Turbo 0125
by azure|1970-01-01|16K context

Gpt 35 Turbo 0125 supports text input and text output with 16K context, suited for cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 35 Turbo 16k
by azure|1970-01-01|16K context

Gpt 35 Turbo 16k supports text input and text output with 16K context.

$3 /M input$4 /M outputspeed —synced 2026-05-13
a
Gpt 35 Turbo 16k 0613
by azure|1970-01-01|16K context

Gpt 35 Turbo 16k 0613 supports text input and text output with 16K context.

$3 /M input$4 /M outputspeed —synced 2026-05-13
a
Gpt 35 Turbo Instruct
by azure|1970-01-01|4K context

Gpt 35 Turbo Instruct supports text input and text output with 4K context.

$1.5 /M input$2 /M outputspeed —synced 2026-05-13
a
Gpt 4
by azure|1970-01-01|33K context

Gpt 4 supports text input and text output with 33K context.

$30 /M input$60 /M outputspeed —synced 2026-05-13
a
Gpt 4 Turbo
by azure|1970-01-01|128K context

Gpt 4 Turbo supports text input and text output with 128K context.

$10 /M input$30 /M outputspeed —synced 2026-05-13
a
Gpt 5.3 Chat
by azure|1970-01-01|128K context

Gpt 5.3 Chat supports text input and text output with 128K context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-13
a
Gpt 4 1106 Preview
by azure|1970-01-01|128K context

Gpt 4 1106 Preview supports text input and text output with 128K context.

$10 /M input$30 /M outputspeed —synced 2026-05-13
a
Gpt 4 32k
by azure|1970-01-01|33K context

Gpt 4 32k supports text input and text output with 33K context.

$60 /M input$120 /M outputspeed —synced 2026-05-13
a
Gpt 4 32k 0613
by azure|1970-01-01|33K context

Gpt 4 32k 0613 supports text input and text output with 33K context.

$60 /M input$120 /M outputspeed —synced 2026-05-13
a
Gpt 4 Turbo 2024 04 09
by azure|1970-01-01|128K context

Gpt 4 Turbo 2024 04 09 supports text input and text output with 128K context.

$10 /M input$30 /M outputspeed —synced 2026-05-12
a
Gpt 4 Turbo Vision Preview
by azure|1970-01-01|128K context

Gpt 4 Turbo Vision Preview supports text input and text output with 128K context.

$10 /M input$30 /M outputspeed —synced 2026-05-13
a
Gpt 4.1
by azure|1970-01-01|1.0M context

Gpt 4.1 supports text input and text output with 1.0M context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 4.1 Mini
by azure|1970-01-01|1.0M context

Gpt 4.1 Mini supports text input and text output with 1.0M context, suited for long context, cheap batch.

$0.4 /M input$1.6 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt 4.1 Mini 2025 04 14
by azure|1970-01-01|1.0M context

Gpt 4.1 Mini 2025 04 14 supports text input and text output with 1.0M context, suited for long context, cheap batch.

$0.4 /M input$1.6 /M outputspeed —synced 2026-05-12
Long contextCheap batch
a
Gpt 4.1 Nano 2025 04 14
by azure|1970-01-01|1.0M context

Gpt 4.1 Nano 2025 04 14 supports text input and text output with 1.0M context, suited for long context, cheap batch.

$0.1 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt 4.5 Preview
by azure|1970-01-01|128K context

Gpt 4.5 Preview supports text input and text output with 128K context.

$75 /M input$150 /M outputspeed —synced 2026-05-13
a
Gpt 4o 2024 05 13
by azure|1970-01-01|128K context

Gpt 4o 2024 05 13 supports text input and text output with 128K context.

$5 /M input$15 /M outputspeed —synced 2026-05-12
a
Gpt Audio 2025 08 28
by azure|1970-01-01|128K context

Gpt Audio 2025 08 28 supports text input and text output with 128K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt Audio 1.5 2026 02 23
by azure|1970-01-01|128K context

Gpt Audio 1.5 2026 02 23 supports text input and text output with 128K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-13
a
Gpt Audio Mini 2025 10 06
by azure|1970-01-01|128K context

Gpt Audio Mini 2025 10 06 supports text input and text output with 128K context.

$0.6 /M input$2.4 /M outputspeed —synced 2026-05-12
a
Gpt 4o Audio Preview 2024 12 17
by azure|1970-01-01|128K context

Gpt 4o Audio Preview 2024 12 17 supports text input and text output with 128K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt 4o Mini Audio Preview 2024 12 17
by azure|1970-01-01|128K context

Gpt 4o Mini Audio Preview 2024 12 17 supports text input and text output with 128K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt Realtime 2025 08 28
by azure|1970-01-01|32K context

Gpt Realtime 2025 08 28 supports text input and text output with 32K context.

$4 /M input$16 /M outputspeed —synced 2026-05-12
a
Gpt Realtime 1.5 2026 02 23
by azure|1970-01-01|32K context

Gpt Realtime 1.5 2026 02 23 supports text input and text output with 32K context.

$4 /M input$16 /M outputspeed —synced 2026-05-13
a
Gpt 4o Mini Transcribe
by azure|1970-01-01|16K context

Gpt 4o Mini Transcribe supports text input and text output with 16K context.

$1.25 /M input$5 /M outputspeed —synced 2026-05-12
a
Gpt 4o Mini Tts
by azure|1970-01-01|0K context

Gpt 4o Mini Tts supports text input and text output with 0K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt 4o Transcribe
by azure|1970-01-01|16K context

Gpt 4o Transcribe supports text input and text output with 16K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt 4o Transcribe Diarize
by azure|1970-01-01|16K context

Gpt 4o Transcribe Diarize supports text input and text output with 16K context.

$2.5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt 5.1 2025 11 13
by azure|1970-01-01|272K context

Gpt 5.1 2025 11 13 supports text input and text output with 272K context, suited for long context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.1 Codex Mini 2025 11 13
by azure|1970-01-01|272K context

Gpt 5.1 Codex Mini 2025 11 13 supports text input and text output with 272K context, suited for long context, cheap batch.

$0.25 /M input$2 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt 5
by azure|1970-01-01|272K context

Gpt 5 supports text input and text output with 272K context, suited for long context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5 Chat
by azure|1970-01-01|128K context

Gpt 5 Chat supports text input and text output with 128K context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-13
a
Gpt 5 Chat Latest
by azure|1970-01-01|128K context

Gpt 5 Chat Latest supports text input and text output with 128K context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt 5 Codex
by azure|1970-01-01|400K context

Gpt 5 Codex supports text input and text output with 400K context, suited for long context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5 Nano
by azure|1970-01-01|400K context

Gpt 5 Nano supports text input and text output with 400K context, suited for long context, cheap batch.

$0.05 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt 5 Pro
by azure|1970-01-01|400K context

Gpt 5 Pro supports text input and text output with 400K context, suited for long context.

$15 /M input$120 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.1 Codex Max
by azure|1970-01-01|272K context

Gpt 5.1 Codex Max supports text input and text output with 272K context, suited for long context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.2
by azure|1970-01-01|272K context

Gpt 5.2 supports text input and text output with 272K context, suited for long context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.2 2025 12 11
by azure|1970-01-01|272K context

Gpt 5.2 2025 12 11 supports text input and text output with 272K context, suited for long context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.2 Chat
by azure|1970-01-01|128K context

Gpt 5.2 Chat supports text input and text output with 128K context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-13
a
Gpt 5.2 Codex
by azure|1970-01-01|272K context

Gpt 5.2 Codex supports text input and text output with 272K context, suited for long context.

$1.75 /M input$14 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.2 Pro
by azure|1970-01-01|400K context

Gpt 5.2 Pro supports text input and text output with 400K context, suited for long context.

$21 /M input$168 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.2 Pro 2025 12 11
by azure|1970-01-01|272K context

Gpt 5.2 Pro 2025 12 11 supports text input and text output with 272K context, suited for long context.

$21 /M input$168 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4
by azure|1970-01-01|1.1M context

Gpt 5.4 supports text input and text output with 1.1M context, suited for long context.

$2.5 /M input$15 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4 2026 03 05
by azure|1970-01-01|1.1M context

Gpt 5.4 2026 03 05 supports text input and text output with 1.1M context, suited for long context.

$2.5 /M input$15 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4 Pro
by azure|1970-01-01|1.1M context

Gpt 5.4 Pro supports text input and text output with 1.1M context, suited for long context.

$30 /M input$180 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4 Pro 2026 03 05
by azure|1970-01-01|1.1M context

Gpt 5.4 Pro 2026 03 05 supports text input and text output with 1.1M context, suited for long context.

$30 /M input$180 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.5
by azure|1970-01-01|1.1M context

Gpt 5.5 supports text input and text output with 1.1M context, suited for long context.

$5 /M input$30 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.5 2026 04 23
by azure|1970-01-01|1.1M context

Gpt 5.5 2026 04 23 supports text input and text output with 1.1M context, suited for long context.

$5 /M input$30 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.5 Pro
by azure|1970-01-01|1.1M context

Gpt 5.5 Pro supports text input and text output with 1.1M context, suited for long context.

$30 /M input$180 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.5 Pro 2026 04 23
by azure|1970-01-01|1.1M context

Gpt 5.5 Pro 2026 04 23 supports text input and text output with 1.1M context, suited for long context.

$30 /M input$180 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4 Mini
by azure|1970-01-01|1.1M context

Gpt 5.4 Mini supports text input and text output with 1.1M context, suited for long context.

$0.75 /M input$4.5 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 5.4 Mini 2026 03 17
by azure|1970-01-01|1.1M context

Gpt 5.4 Mini 2026 03 17 supports text input and text output with 1.1M context, suited for long context.

$0.75 /M input$4.5 /M outputspeed —synced 2026-05-12
Long context
a
Gpt 5.4 Nano
by azure|1970-01-01|1.1M context

Gpt 5.4 Nano supports text input and text output with 1.1M context, suited for long context, cheap batch.

$0.2 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt 5.4 Nano 2026 03 17
by azure|1970-01-01|1.1M context

Gpt 5.4 Nano 2026 03 17 supports text input and text output with 1.1M context, suited for long context, cheap batch.

$0.2 /M input$1.25 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Gpt Image 1 Mini
by azure|1970-01-01|0K context

Gpt Image 1 Mini supports text input and text output with 0K context.

$2 /M inputFree /M outputspeed —synced 2026-05-12
a
Gpt Image 1.5
by azure|1970-01-01|0K context

Gpt Image 1.5 supports text input and text output with 0K context.

$5 /M inputFree /M outputspeed —synced 2026-05-12
a
Gpt Image 1.5 2025 12 16
by azure|1970-01-01|0K context

Gpt Image 1.5 2025 12 16 supports text input and text output with 0K context.

$5 /M inputFree /M outputspeed —synced 2026-05-12
a
Gpt Image 2
by azure|1970-01-01|0K context

Gpt Image 2 supports text input and text output with 0K context.

$5 /M input$10 /M outputspeed —synced 2026-05-12
a
Gpt Image 2 2026 04 21
by azure|1970-01-01|0K context

Gpt Image 2 2026 04 21 supports text input and text output with 0K context.

$5 /M input$10 /M outputspeed —synced 2026-05-12
a
Mistral Large 2402
by azure|1970-01-01|32K context

Mistral Large 2402 supports text input and text output with 32K context.

$8 /M input$24 /M outputspeed —synced 2026-05-13
a
Mistral Large Latest
by azure|1970-01-01|32K context

Mistral Large Latest supports text input and text output with 32K context.

$8 /M input$24 /M outputspeed —synced 2026-05-12
a
O1 Mini
by azure|1970-01-01|128K context

O1 Mini supports text input and text output with 128K context.

$1.21 /M input$4.84 /M outputspeed —synced 2026-05-13
a
O1 Preview
by azure|1970-01-01|128K context

O1 Preview supports text input and text output with 128K context.

$15 /M input$60 /M outputspeed —synced 2026-05-13
a
O3
by azure|1970-01-01|200K context

O3 supports text input and text output with 200K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
O3 2025 04 16
by azure|1970-01-01|200K context

O3 2025 04 16 supports text input and text output with 200K context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-13
Long context
a
Tts 1 Hd
by azure|1970-01-01|0K context

Tts 1 Hd supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
O4 Mini
by azure|1970-01-01|200K context

O4 Mini supports text input and text output with 200K context, suited for long context.

$1.1 /M input$4.4 /M outputspeed —synced 2026-05-13
Long context
a
Text Embedding 3 Large
by azure|1970-01-01|8K context

Text Embedding 3 Large supports text input and text output with 8K context, suited for cheap batch.

$0.13 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Text Embedding 3 Small
by azure|1970-01-01|8K context

Text Embedding 3 Small supports text input and text output with 8K context, suited for cheap batch.

$0.02 /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Text Embedding Ada 002
by azure|1970-01-01|8K context

Text Embedding Ada 002 supports text input and text output with 8K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Azure Tts
by azure|1970-01-01|0K context

Azure Tts supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Azure Tts Hd
by azure|1970-01-01|0K context

Azure Tts Hd supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 4.1 2025 04 14
by azure|1970-01-01|1.0M context

Gpt 4.1 2025 04 14 supports text input and text output with 1.0M context, suited for long context.

$2 /M input$8 /M outputspeed —synced 2026-05-12
Long context
a
Whisper 1
by azure|1970-01-01|0K context

Whisper 1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 4 0125 Preview
by azure|1970-01-01|128K context

Gpt 4 0125 Preview supports text input and text output with 128K context.

$10 /M input$30 /M outputspeed —synced 2026-05-13
a
Gpt 4.1 Nano
by azure|1970-01-01|1.0M context

Gpt 4.1 Nano supports text input and text output with 1.0M context, suited for long context, cheap batch.

$0.1 /M input$0.4 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Tts 1
by azure|1970-01-01|0K context

Tts 1 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Gpt 4 0613
by azure|1970-01-01|33K context

Gpt 4 0613 supports text input and text output with 33K context.

$30 /M input$60 /M outputspeed —synced 2026-05-13
a
O3 Mini
by azure|1970-01-01|200K context

O3 Mini supports text input and text output with 200K context, suited for long context.

$1.1 /M input$4.4 /M outputspeed —synced 2026-05-13
Long context
a
O3 Pro 2025 06 10
by azure|1970-01-01|200K context

O3 Pro 2025 06 10 supports text input and text output with 200K context, suited for long context.

$20 /M input$80 /M outputspeed —synced 2026-05-13
Long context
a
Codex Mini
by azure|1970-01-01|200K context

Codex Mini supports text input and text output with 200K context, suited for long context.

$1.5 /M input$6 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 35 Turbo 1106
by azure|1970-01-01|16K context

Gpt 35 Turbo 1106 supports text input and text output with 16K context.

$1 /M input$2 /M outputspeed —synced 2026-05-13
a
Gpt 35 Turbo Instruct 0914
by azure|1970-01-01|4K context

Gpt 35 Turbo Instruct 0914 supports text input and text output with 4K context.

$1.5 /M input$2 /M outputspeed —synced 2026-05-13
a
Gpt 5.1 Chat 2025 11 13
by azure|1970-01-01|128K context

Gpt 5.1 Chat 2025 11 13 supports text input and text output with 128K context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-13
a
Gpt 5.1 Codex 2025 11 13
by azure|1970-01-01|272K context

Gpt 5.1 Codex 2025 11 13 supports text input and text output with 272K context, suited for long context.

$1.25 /M input$10 /M outputspeed —synced 2026-05-13
Long context
a
O4 Mini 2025 04 16
by azure|1970-01-01|200K context

O4 Mini 2025 04 16 supports text input and text output with 200K context, suited for long context.

$1.1 /M input$4.4 /M outputspeed —synced 2026-05-13
Long context
a
O3 Pro
by azure|1970-01-01|200K context

O3 Pro supports text input and text output with 200K context, suited for long context.

$20 /M input$80 /M outputspeed —synced 2026-05-13
Long context
a
Sora 2
by azure|1970-01-01|0K context

Sora 2 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Sora 2 Pro High Res
by azure|1970-01-01|0K context

Sora 2 Pro High Res supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Sora 2 Pro
by azure|1970-01-01|0K context

Sora 2 Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
a
Container
by azure|1970-01-01|0K context

Container supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
O3 Deep Research
by azure|1970-01-01|200K context

O3 Deep Research supports text input and text output with 200K context, suited for long context.

$10 /M input$40 /M outputspeed —synced 2026-05-13
Long context
a
Gpt 4o 2024 11 20
by azure|1970-01-01|128K context

Gpt 4o 2024 11 20 supports text input and text output with 128K context.

$2.75 /M input$11 /M outputspeed —synced 2026-05-13
a
Gpt Image 1
by azure|1970-01-01|0K context

Gpt Image 1 supports text input and text output with 0K context.

$5 /M inputFree /M outputspeed —synced 2026-05-13
a
Claude Opus 4 5
by azure_ai|1970-01-01|410K context

Claude Opus 4 5 supports text input and text output with 410K context, suited for long context.

$5 /M input$25 /M outputspeed —synced 2026-05-13
Long context
a
Claude Opus 4 1
by azure_ai|1970-01-01|200K context

Claude Opus 4 1 supports text input and text output with 200K context, suited for long context.

$15 /M input$75 /M outputspeed —synced 2026-05-13
Long context
a
Claude Sonnet 4 5
by azure_ai|1970-01-01|1M context

Claude Sonnet 4 5 supports text input and text output with 1M context, suited for long context.

$3 /M input$15 /M outputspeed —synced 2026-05-13
Long context
a
Model Router
by azure_ai|1970-01-01|0K context

Model Router supports text input and text output with 0K context, suited for cheap batch.

$0.14 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3 Small 8k Instruct
by azure_ai|1970-01-01|8K context

Phi 3 Small 8k Instruct supports text input and text output with 8K context, suited for cheap batch.

$0.15 /M input$0.6 /M outputspeed —synced 2026-05-13
Cheap batch
a
Llama 3.3 70B Instruct
by azure_ai|1970-01-01|128K context

Llama 3.3 70B Instruct supports text input and text output with 128K context.

$0.71 /M input$0.71 /M outputspeed —synced 2026-05-13
a
Llama 3.2 11B Vision Instruct
by azure_ai|1970-01-01|128K context

Llama 3.2 11B Vision Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.37 /M input$0.37 /M outputspeed —synced 2026-05-13
Cheap batch
a
Claude Opus 4 6
by azure_ai|1970-01-01|1M context

Claude Opus 4 6 supports text input and text output with 1M context, suited for long context.

$5 /M input$25 /M outputspeed —synced 2026-05-13
Long context
a
Cohere Embed V3 Multilingual
by azure_ai|1970-01-01|1K context

Cohere Embed V3 Multilingual supports text input and text output with 1K context, suited for cheap batch.

$0.1 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
FLUX 1.1 Pro
by azure_ai|1970-01-01|0K context

FLUX 1.1 Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Flux.2 Pro
by azure_ai|1970-01-01|0K context

Flux.2 Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Llama 3.2 90B Vision Instruct
by azure_ai|1970-01-01|128K context

Llama 3.2 90B Vision Instruct supports text input and text output with 128K context.

$2.04 /M input$2.04 /M outputspeed —synced 2026-05-13
a
Llama 4 Maverick 17B 128E Instruct FP8
by azure_ai|1970-01-01|1M context

Llama 4 Maverick 17B 128E Instruct FP8 supports text input and text output with 1M context, suited for long context.

$1.41 /M input$0.35 /M outputspeed —synced 2026-05-13
Long context
a
Llama 4 Scout 17B 16E Instruct
by azure_ai|1970-01-01|10M context

Llama 4 Scout 17B 16E Instruct supports text input and text output with 10M context, suited for long context, cheap batch.

$0.2 /M input$0.78 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Meta Llama 3.1 405B Instruct
by azure_ai|1970-01-01|128K context

Meta Llama 3.1 405B Instruct supports text input and text output with 128K context.

$5.33 /M input$16 /M outputspeed —synced 2026-05-13
a
Phi 3 Medium 128k Instruct
by azure_ai|1970-01-01|128K context

Phi 3 Medium 128k Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.17 /M input$0.68 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3 Medium 4k Instruct
by azure_ai|1970-01-01|4K context

Phi 3 Medium 4k Instruct supports text input and text output with 4K context, suited for cheap batch.

$0.17 /M input$0.68 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3 Mini 128k Instruct
by azure_ai|1970-01-01|131K context

Phi 3 Mini 128k Instruct supports text input and text output with 131K context, suited for cheap batch.

$0.13 /M input$0.52 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3 Mini 4k Instruct
by azure_ai|1970-01-01|4K context

Phi 3 Mini 4k Instruct supports text input and text output with 4K context, suited for cheap batch.

$0.13 /M input$0.52 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3 Small 128k Instruct
by azure_ai|1970-01-01|128K context

Phi 3 Small 128k Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.15 /M input$0.6 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3.5 MoE Instruct
by azure_ai|1970-01-01|128K context

Phi 3.5 MoE Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.16 /M input$0.64 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3.5 Mini Instruct
by azure_ai|1970-01-01|128K context

Phi 3.5 Mini Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.13 /M input$0.52 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 4 Mini Instruct
by azure_ai|1970-01-01|131K context

Phi 4 Mini Instruct supports text input and text output with 131K context, suited for cheap batch.

$0.075 /M input$0.3 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 4 Multimodal Instruct
by azure_ai|1970-01-01|131K context

Phi 4 Multimodal Instruct supports text input and text output with 131K context, suited for cheap batch.

$0.08 /M input$0.32 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral Document Ai 2505
by azure_ai|1970-01-01|0K context

Mistral Document Ai 2505 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral Document Ai 2512
by azure_ai|1970-01-01|0K context

Mistral Document Ai 2512 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Prebuilt Read
by azure_ai|1970-01-01|0K context

Prebuilt Read supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Prebuilt Document
by azure_ai|1970-01-01|0K context

Prebuilt Document supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
MAI DS R1
by azure_ai|1970-01-01|128K context

MAI DS R1 supports text input and text output with 128K context.

$1.35 /M input$5.4 /M outputspeed —synced 2026-05-13
a
Cohere Rerank V3 English
by azure_ai|1970-01-01|4K context

Cohere Rerank V3 English supports text input and text output with 4K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Cohere Rerank V3.5
by azure_ai|1970-01-01|4K context

Cohere Rerank V3.5 supports text input and text output with 4K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Cohere Rerank V4.0 Pro
by azure_ai|1970-01-01|33K context

Cohere Rerank V4.0 Pro supports text input and text output with 33K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Cohere Rerank V4.0 Fast
by azure_ai|1970-01-01|33K context

Cohere Rerank V4.0 Fast supports text input and text output with 33K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Deepseek V3.2
by azure_ai|1970-01-01|164K context

Deepseek V3.2 supports text input and text output with 164K context.

$0.58 /M input$1.68 /M outputspeed —synced 2026-05-13
a
Deepseek V3
by azure_ai|1970-01-01|128K context

Deepseek V3 supports text input and text output with 128K context.

$1.14 /M input$4.56 /M outputspeed —synced 2026-05-12
a
Deepseek V3 0324
by azure_ai|1970-01-01|128K context

Deepseek V3 0324 supports text input and text output with 128K context.

$1.14 /M input$4.56 /M outputspeed —synced 2026-05-12
a
Embed V 4 0
by azure_ai|1970-01-01|128K context

Embed V 4 0 supports text input and text output with 128K context, suited for cheap batch.

$0.12 /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Grok 3 Mini
by azure_ai|1970-01-01|131K context

Grok 3 Mini supports text input and text output with 131K context, suited for cheap batch.

$0.25 /M input$1.27 /M outputspeed —synced 2026-05-13
Cheap batch
a
Grok 4 Fast Non Reasoning
by azure_ai|1970-01-01|2M context

Grok 4 Fast Non Reasoning supports text input and text output with 2M context, suited for long context, cheap batch.

$0.2 /M input$0.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Grok 4 Fast Reasoning
by azure_ai|1970-01-01|2M context

Grok 4 Fast Reasoning supports text input and text output with 2M context, suited for long context, cheap batch.

$0.2 /M input$0.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Grok Code Fast 1
by azure_ai|1970-01-01|256K context

Grok Code Fast 1 supports text input and text output with 256K context, suited for long context, cheap batch.

$0.2 /M input$1.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Jais 30b Chat
by azure_ai|1970-01-01|8K context

Jais 30b Chat supports text input and text output with 8K context.

$3,200 /M input$9,710 /M outputspeed —synced 2026-05-13
a
Jamba Instruct
by azure_ai|1970-01-01|256K context

Jamba Instruct supports text input and text output with 256K context, suited for long context, cheap batch.

$0.5 /M input$0.7 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Ministral 3b
by azure_ai|1970-01-01|128K context

Ministral 3b supports text input and text output with 128K context, suited for cheap batch.

$0.04 /M input$0.04 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral Large 3
by azure_ai|1970-01-01|262K context

Mistral Large 3 supports text input and text output with 262K context, suited for long context, cheap batch.

$0.5 /M input$1.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Mistral Medium 2505
by azure_ai|1970-01-01|131K context

Mistral Medium 2505 supports text input and text output with 131K context, suited for cheap batch.

$0.4 /M input$2 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral Nemo
by azure_ai|1970-01-01|131K context

Mistral Nemo supports text input and text output with 131K context, suited for cheap batch.

$0.15 /M input$0.15 /M outputspeed —synced 2026-05-13
Cheap batch
a
Mistral Small
by azure_ai|1970-01-01|32K context

Mistral Small supports text input and text output with 32K context.

$1 /M input$3 /M outputspeed —synced 2026-05-13
a
Mistral Small 2503
by azure_ai|1970-01-01|128K context

Mistral Small 2503 supports text input and text output with 128K context, suited for cheap batch.

$0.1 /M input$0.3 /M outputspeed —synced 2026-05-13
Cheap batch
a
Deepseek V3.2 Speciale
by azure_ai|1970-01-01|164K context

Deepseek V3.2 Speciale supports text input and text output with 164K context.

$0.58 /M input$1.68 /M outputspeed —synced 2026-05-13
a
Gpt Oss 120b
by azure_ai|1970-01-01|131K context

Gpt Oss 120b supports text input and text output with 131K context, suited for cheap batch.

$0.15 /M input$0.6 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 4 Reasoning
by azure_ai|1970-01-01|33K context

Phi 4 Reasoning supports text input and text output with 33K context, suited for cheap batch.

$0.125 /M input$0.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
Grok 4 1 Fast Non Reasoning
by azure_ai|1970-01-01|2M context

Grok 4 1 Fast Non Reasoning supports text input and text output with 2M context, suited for long context, cheap batch.

$0.2 /M input$0.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Mistral Large Latest
by azure_ai|1970-01-01|262K context

Mistral Large Latest supports text input and text output with 262K context, suited for long context.

$2 /M input$6 /M outputspeed —synced 2026-05-13
Long context
a
Grok 4 1 Fast Reasoning
by azure_ai|1970-01-01|2M context

Grok 4 1 Fast Reasoning supports text input and text output with 2M context, suited for long context, cheap batch.

$0.2 /M input$0.5 /M outputspeed —synced 2026-05-13
Long contextCheap batch
a
Phi 4 Mini Reasoning
by azure_ai|1970-01-01|131K context

Phi 4 Mini Reasoning supports text input and text output with 131K context, suited for cheap batch.

$0.08 /M input$0.32 /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 4
by azure_ai|1970-01-01|16K context

Phi 4 supports text input and text output with 16K context, suited for cheap batch.

$0.125 /M input$0.5 /M outputspeed —synced 2026-05-13
Cheap batch
a
FLUX.1 Kontext Pro
by azure_ai|1970-01-01|0K context

FLUX.1 Kontext Pro supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Prebuilt Layout
by azure_ai|1970-01-01|0K context

Prebuilt Layout supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
a
Phi 3.5 Vision Instruct
by azure_ai|1970-01-01|128K context

Phi 3.5 Vision Instruct supports text input and text output with 128K context, suited for cheap batch.

$0.13 /M input$0.52 /M outputspeed —synced 2026-05-13
Cheap batch
b
Baichuan-Omni-1.5
by baichuan|1970-01-01|0K context

Baichuan-Omni-1.5 supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
b
Baichuan-Omni
by baichuan-westlake-university-zhejiang-university-zju|1970-01-01|0K context

Baichuan-Omni supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
B
ERNIE-4.5-300B-A47B
by baidu|1970-01-01|123K context

ERNIE-4.5-300B-A47B supports text input and text output with 123K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-13
Cheap batch
B
ERNIE-4.5-0.3B
by baidu|1970-01-01|0K context

ERNIE-4.5-0.3B supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
B
ERNIE-4.5-VL-424B-A47B (文心大模型4.5)
by baidu|1970-01-01|0K context

ERNIE-4.5-VL-424B-A47B (文心大模型4.5) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
B
ERNIE x1 (文心大模型X1)
by baidu|1970-01-01|0K context

ERNIE x1 (文心大模型X1) supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
b
RNA-DCGen
by bangladesh-university-of-engineering-and-technology-university-of-california-riverside|1970-01-01|0K context

RNA-DCGen supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
b
BiRNA-BERT
by bangladesh-university-of-engineering-and-technology-university-of-california-riverside-carnegie-mellon-university-cmu|1970-01-01|0K context

BiRNA-BERT supports text input and text output with 0K context, suited for cheap batch.

Free /M inputFree /M outputspeed —synced 2026-05-12
Cheap batch
b
MiniMax M2.5
by baseten|1970-01-01|197K context

MiniMax M2.5 supports text input and text output with 197K context, suited for cheap batch.

$0.3 /M input$1.2 /M outputspeed —synced 2026-05-13
Cheap batch
b
Nemotron 120B A12B
by baseten|1970-01-01|0K context

Nemotron 120B A12B supports text input and text output with 0K context, suited for cheap batch.

$0.3 /M input$0.75 /M outputspeed —synced 2026-05-13
Cheap batch
b
GLM 4.7
by baseten|1970-01-01|205K context

GLM 4.7 supports text input and text output with 205K context, suited for long context.

$0.6 /M input$2.2 /M outputspeed —synced 2026-05-13
Long context
b
Kimi K2 Thinking
by baseten|1970-01-01|0K context

Kimi K2 Thinking supports text input and text output with 0K context.

$0.6 /M input$2.5 /M outputspeed —synced 2026-05-12
500 models shown.0 models selected for comparison.