Introducing Baseten Loops: A Training SDK for Frontier RL. Learn more here
large language

MiniMaxMiniMax M3

MiniMax M3 delivers frontier performance for coding and agentic tasks. The model pairs a 1 million token context window with native multimodal input.

Model details

Example usage

MiniMax M3 is a 427B parameter MoE model with 23B active parameters. It scores competitively across benchmarks for coding, agentic tool use, and multimodal tasks.

MiniMax M3MiniMax M3

Input
JSON output
1{
2    "id": "143",
3    "choices": [
4        {
5            "finish_reason": "stop",
6            "index": 0,
7            "logprobs": null,
8            "message": {
9                "content": "[Model output here]",
10                "role": "assistant",
11                "audio": null,
12                "function_call": null,
13                "tool_calls": null
14            }
15        }
16    ],
17    "created": 1741224586,
18    "model": "",
19    "object": "chat.completion",
20    "service_tier": null,
21    "system_fingerprint": null,
22    "usage": {
23        "completion_tokens": 145,
24        "prompt_tokens": 38,
25        "total_tokens": 183,
26        "completion_tokens_details": null,
27        "prompt_tokens_details": null
28    }
29}

🔥 Trending models