MiniMax-M3 by MiniMax demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Artificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Coding Benchmarks
Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Reasoning Benchmarks
Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 46 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 7 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Kenari | $0 | $0 | — | 1.0M | — |
| MiniMax Token Plan (minimaxi.com) | $0 | $0 | $0 | 1.0M | — |
| MiniMax Token Plan (minimax.io) | $0 | $0 | $0 | 1.0M | — |
| Nvidia | $0 | $0 | — | 1.0M | — |
| SCNet Token Plan | $0 | $0 | $0 | 1.0M | — |
| Volcengine Ark Coding Plan | $0 | $0 | $0 | 1.0M | — |
| EmpirioLabs AI | $0.225 | $0.9 | $0.045 | 1.0M | — |
| Weights & Biases | $0.23 | $0.96 | $0.05 | 262K | — |
| Vancine | $0.24 | $0.96 | $0.048 | 1.0M | — |
| Deep Infra | $0.28 | $1.1 | $0.056 | 524K | Supported |
| Lilac | $0.28 | $1.1 | $0.05 | 1.0M | — |
| Abacus | $0.3 | $1.2 | — | 1.0M | — |
| ClinePass | $0.3 | $1.2 | $0.06 | 1.0M | — |
| DevPass (LLM Gateway) | $0.3 | $1.2 | $0.06 | 1.0M | — |
| Eden AI | $0.3 | $1.2 | $0.06 | 524K | — |
| Fireworks AI | $0.3 | $1.2 | $0.06 | 512K | Supported |
| Hugging Face | $0.3 | $1.2 | — | 524K | Supported |
| Jalapeno Cloud | $0.3 | $1.2 | — | 524K | — |
| Kilo Gateway | $0.3 | $1.2 | $0.06 | 524K | — |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 1.0M | — |
| Merge Gateway | $0.3 | $1.2 | $0.06 | 1.0M | — |
| MiniMax (minimaxi.com) | $0.3 | $1.2 | $0.06 | 1.0M | — |
| MiniMax (minimax.io) | $0.3 | $1.2 | $0.06 | 1.0M | Supported |
| NanoGPT | $0.3 | $1.2 | $0.06 | 512K | — |
| Nebius Token Factory | $0.3 | $1.2 | — | 1.0M | — |
| OpenCode Go | $0.3 | $1.2 | $0.06 | 1.0M | — |
| OpenCode Zen | $0.3 | $1.2 | $0.06 | 512K | — |
| OpenRouter | $0.3 | $1.2 | $0.06 | 1.0M | Supported |
| OrcaRouter | $0.3 | $1.2 | $0.06 | 1.0M | — |
| Pioneer | $0.3 | $1.2 | $0.06 | 1.0M | — |
| Together AI | $0.3 | $1.2 | $0.06 | 524K | Supported |
| Venice AI | $0.3 | $1.2 | $0.06 | 524K | — |
| Vercel AI Gateway | $0.3 | $1.2 | $0.06 | 512K | Supported |
| Charm Hyper | $0.32664 | $1.30656 | $0.064239 | 512K | — |
| CrossModel | $0.33 | $1.32 | $0.066 | 1.0M | — |
| Wafer | $0.33 | $1.32 | $0.07 | 1.0M | — |
| Cortecs | $0.395 | $1.977 | $0.099 | 1.0M | — |
| Requesty | $0.4 | $2 | $0.1 | 1.0M | — |
| TensorX | $0.4 | $2 | $0.1 | 1.0M | — |
| GMI Cloud | $0.6 | $2.4 | $0.12 | 1.0M | — |
| Ofox | $0.6 | $2.4 | $0.12 | 1.0M | — |
| Opper | $0.6 | $2.4 | $0.12 | 1.0M | — |
| Synthetic | $0.6 | $1.2 | $0.6 | 524K | — |
| ZenMux | $0.6 | $2.4 | — | 1.0M | — |
| 302.AI | $0.72 | $2.88 | — | 1.0M | — |
| Ollama Cloud | — | — | — | 512K | — |
MiniMax-M3 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare MiniMax-M3 With
MiniMax-M3 — Frequently Asked Questions
How much does MiniMax-M3 cost?
MiniMax-M3 costs $0.30 per 1M input tokens and $1.2 per 1M output tokens. This makes it one of the more affordable models.
What is the context window of MiniMax-M3?
MiniMax-M3 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created MiniMax-M3?
MiniMax-M3 was created by MiniMax. It is classified as a open source model in our catalogue.
Is MiniMax-M3 open source?
Yes, MiniMax-M3 is an open-source model. The model weights are publicly available for download and self-hosting.