MiniMax
Open-weight multimodal models built for long agent runs.
MiniMax publishes open weights for its M-series models, which are aimed at long-horizon agentic work and coding. The current M3 takes text, images and video with a million-token context, and the older M2 models are still around and cheaper. A solid middle option: more capable than the tiny Flash models, far cheaper than a frontier API, and you can host it yourself if you need to.
At a glance — MiniMax M3
- Cost
- $0.30 in · $1.20 out per 1M tokensBudget
- Memory
- 1M tokens — about 1,550 pages
- Reads
- Text · Images · Video
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 66% · Agentic work: better than 67% · Overall: better than 54%
- Reliability
- 99.96% uptime, last 24h
- Released
- May 31, 2026
Advanced details
- API model ID
minimax/minimax-m3- Max output
- 512K tokens
- Max input
- 524K tokens
- Cached input
- $0.06 per 1M
- Tokenizer
- Other
- Coding index
- 58.6
- Agentic work index
- 29.5
- Overall index
- 29.2
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| CoreWeave · fp4 | $0.23 | $0.96 | $0.05 | 236K | 97.82% |
| GMICloud · fp8 | $0.24 | $0.96 | $0.048 | 524K | 99.82% |
| DeepInfra · fp8 | $0.28 | $1.10 | $0.056 | 512K | 99.83% |
| StreamLake · fp8 | $0.30 | $1.20 | $0.06 | 512K | 99.57% |
| Venice · fp8 | $0.30 | $1.20 | $0.06 | 66K | 93.43% |
| Together | $0.30 | $1.20 | $0.06 | 472K | 99.96% |
| Parasail · fp8 | $0.30 | $1.20 | $0.06 | 524K | 99.80% |
| AtlasCloud · fp8 | $0.30 | $1.20 | $0.06 | 524K | 97.74% |
| Novita · fp8 | $0.30 | $1.20 | $0.06 | 131K | 99.90% |
| Minimax · fp8 | $0.30 | $1.20 | $0.06 | 512K | 99.84% |
| MaraDegraded | $0.60 | $2.40 | — | 944K | 92.87% |
| SambaNova | $0.60 | $2.40 | — | 944K | 97.72% |
| ModelRun · fp4 | $0.75 | $3.00 | $0.15 | 944K | 99.45% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Expert
- Made by
- MiniMax
- Weights
- Open
- Good for
- Agentic work over a long context