MiniMax
MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
Model facts
- Context window
- 1.05M tokens
- Maximum output
- 512K tokens
- Cheapest paid input
- $0.225 per 1M tokens
- Cheapest paid output
- $0.9 per 1M tokens
- Open weights
- yes
- Providers
- 51
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video, pdf.
Local hardware estimate
At 4K context: Q4_K_M 262.3 GiB, Q8_0 461.2 GiB, F16 834.1 GiB working memory.
- Parameters
- 427.0 billion
- Architecture
- minimaxm3sparse
- Model license
- other
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 45.4 | 58.6 | not measured | 77.1 |
Observed price history
- 2026-08-24: $0.225 input / $0.9 output per 1M tokens
API providers
- Kenari — model id minimax-m3; free input / free output per 1M tokens; provider documentation
- Kilo Gateway — model id minimax/minimax-m3:free; free input / free output per 1M tokens; provider documentation
- MiniMax Token Plan (minimax.io) — model id MiniMax-M3; free input / free output per 1M tokens; provider documentation
- MiniMax Token Plan (minimaxi.com) — model id MiniMax-M3; free input / free output per 1M tokens; provider documentation
- Nvidia — model id minimaxai/minimax-m3; free input / free output per 1M tokens; provider documentation
- OpenRouter — model id minimax/minimax-m3:free; free input / free output per 1M tokens; provider documentation
- SCNet Token Plan — model id MiniMax-M3; free input / free output per 1M tokens; provider documentation
- Vercel AI Gateway — model id minimax/minimax-m3-free; free input / free output per 1M tokens; provider documentation
- Volcengine Ark Coding Plan — model id minimax-m3; free input / free output per 1M tokens; provider documentation
- EmpirioLabs AI — model id minimax-m3; $0.225 input / $0.9 output per 1M tokens; provider documentation
- Weights & Biases — model id MiniMaxAI/MiniMax-M3; $0.23 input / $0.96 output per 1M tokens; provider documentation
- Vancine — model id MiniMax-M3; $0.24 input / $0.96 output per 1M tokens; provider documentation
- Deep Infra — model id MiniMaxAI/MiniMax-M3; $0.28 input / $1.1 output per 1M tokens; provider documentation
- Lilac — model id minimaxai/minimax-m3; $0.28 input / $1.1 output per 1M tokens; provider documentation
- Abacus — model id MiniMaxAI/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- ClinePass — model id cline-pass/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Eden AI — model id minimax/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Fireworks AI — model id accounts/fireworks/models/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Hugging Face — model id MiniMaxAI/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Jalapeno Cloud — model id MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Kilo Gateway — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- LLM Gateway — model id together-ai/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Merge Gateway — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- MiniMax (minimax.io) — model id MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- MiniMax (minimaxi.com) — model id MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- NanoGPT — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Nebius Token Factory — model id MiniMaxAI/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OpenCode Go — model id minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OpenCode Zen — model id minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OpenRouter — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OpenRouter — model id minimax/minimax-m3:batch; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OrcaRouter — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Pioneer — model id MiniMaxAI/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Requesty — model id minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Together AI — model id MiniMaxAI/MiniMax-M3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id minimax/minimax-m3; $0.3 input / $1.2 output per 1M tokens; provider documentation
- Charm Hyper — model id minimax-m3; $0.327 input / $1.31 output per 1M tokens; provider documentation
- CrossModel — model id minimax/minimax-m3; $0.33 input / $1.32 output per 1M tokens; provider documentation
- Wafer — model id MiniMax-M3; $0.33 input / $1.32 output per 1M tokens; provider documentation
- Synthetic — model id hf:MiniMaxAI/MiniMax-M3; $0.6 input / $1.2 output per 1M tokens; provider documentation
- Cortecs — model id minimax-m3; $0.395 input / $1.98 output per 1M tokens; provider documentation
- Requesty (EU) — model id minimax-m3@eu; $0.4 input / $2 output per 1M tokens; provider documentation
- TensorX — model id minimax/minimax-m3; $0.4 input / $2 output per 1M tokens; provider documentation
- GMI Cloud — model id MiniMaxAI/MiniMax-M3; $0.6 input / $2.4 output per 1M tokens; provider documentation
- LLM Gateway — model id minimax/minimax-m3; $0.6 input / $2.4 output per 1M tokens; provider documentation
- Ofox — model id minimax/minimax-m3; $0.6 input / $2.4 output per 1M tokens; provider documentation
- Opper — model id minimax/m3; $0.6 input / $2.4 output per 1M tokens; provider documentation
- ZenMux — model id minimax/minimax-m3; $0.6 input / $2.4 output per 1M tokens; provider documentation
- Arena — model id minimax-m3; not published input / not published output per 1M tokens; provider documentation
- Ollama Cloud — model id minimax-m3; not published input / not published output per 1M tokens; provider documentation