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 M2.5
- Cost
- $0.27 in · $1.08 out per 1M tokensBudget
- Memory
- 205K tokens — about 300 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Reliability
- 100.00% uptime, last 24h
- Released
- Feb 12, 2026
Advanced details
- API model ID
minimax/minimax-m2.5- Max output
- 128K tokens
- Cached input
- $0.027 per 1M
- Tokenizer
- Other
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 |
|---|---|---|---|---|---|
| VeniceDegraded | $0.27 | $0.95 | $0.03 | 33K | 90.84% |
| StreamLake | $0.27 | $1.08 | $0.027 | 128K | 99.76% |
| AtlasCloud · fp8 | $0.295 | $1.20 | $0.06 | 177K | 99.81% |
| DigitalOcean | $0.30 | $1.20 | $0.06 | 59K | 0.00% |
| Friendli | $0.30 | $1.20 | $0.06 | 177K | 100.00% |
| Novita · fp8 | $0.30 | $1.20 | $0.03 | 131K | 99.86% |
| Minimax · fp8 | $0.30 | $1.20 | $0.03 | 131K | 99.87% |
| Minimax · highspeed | $0.60 | $2.40 | $0.06 | 131K | 99.81% |
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.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Expert
- Made by
- MiniMax
- Weights
- Open
- Good for
- Agentic work over a long context