browse · models · Google
Google model — context 2M, capabilities: vision · tool · thinking · json · audio.
| Model ID | gemini-3-pro |
| Provider | |
| Family | Gemini |
| Status | active |
| Input $/MTok | $1.25 |
| Output $/MTok | $10 |
| Cache read $/MTok | — |
| Cache write $/MTok | — |
| Context window | 2,000,000 tokens (2M) |
| Max output | — |
| Input modalities | textimageaudio |
| Output modalities | textaudio |
| Capabilities | visiontoolthinkingjsonaudio |
| Supported parameters | max_tokenstemperaturetop_ptoolstool_choiceresponse_formatstructured_outputsreasoninginclude_reasoning |
| Knowledge cutoff | 2026-02 |
| Release date | 2026-04-01 |
| Last synced | — |
| Deprecated | — |
| Official docs | — |
| Intelligence index | 90 / 100 |
| Throughput | 95 tokens/s |
// claude-desktop / cursor / windsurf
{
"jsonrpc": "2.0",
"method": "tools/call",
"id": 1,
"params": {
"name": "get_model_pricing",
"arguments": { "model_id": "gemini-3-pro" }
}
}curl -X POST https://mcp.aiworkflowmcp.com/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","id":1,"params":{"name":"get_model_pricing","arguments":{"model_id":"gemini-3-pro"}}}'