MiniMax-M3: API pricing, providers and specs
MiniMax-M3 is a text model by MiniMax. 34 providers serve it, from $0.90 to $2.40 /1M; the lowest price is at EmpirioLabs AI.
How MiniMax-M3 compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $0.90 /1M against a median of $1.10; 47% of comparable models cost less.
- Its 1M-token context window is larger than 67% of them (median 262K), about 1500 pages of text.
- On LMArena's WebDev board it ranks #50 of the 64 comparable models scored there.
- 34 providers serve it; 99% of comparable models have fewer.
- Its weights are open under the minimax-community license: commercial use under the maker's terms.
MiniMax-M3 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 EmpirioLabs AI | $0.225/1M | From$0.90/1M | $0.045/1M | 1M |
| APIMart | $0.24/1M | $0.96/1M | — | — |
 CometAPI | $0.24/1M | From$0.96/1M | — | — |
 Boundless | $0.28/1M | $1.10/1M | $0.056/1M | — |
 Hugging Face | $0.28/1M | From$1.10/1M | — | — |
 Deep Infra | $0.28/1M | From$1.10/1M | $0.056/1M | — |
 AIHubMix | $0.288/1M | $1.15/1M | — | 1M |
| MiniMaxOfficial | $0.30/1M | From$1.20/1M | $0.06/1M | — |
| ZenMux | $0.30/1M | From$1.20/1M | $0.06/1M | 1M |
 Requesty | $0.30/1M | From$1.20/1M | $0.06/1M | 512K |
 Novita AI | $0.30/1M | From$1.20/1M | $0.06/1M | — |
 Venice AI | $0.30/1M | $1.20/1M | $0.06/1M | — |
| OpenCode | $0.30/1M | $1.20/1M | $0.06/1M | — |
 OrcaRouter | $0.30/1M | $1.20/1M | $0.06/1M | 1.05M |
| Vercel AI Gateway | $0.30/1M | $1.20/1M | $0.06/1M | 512K |
 SiliconFlow | $0.30/1M | $1.20/1M | $0.06/1M | — |
 Together AI | $0.30/1M | $1.20/1M | $0.06/1M | — |
| OpenRouter | $0.30/1M | From$1.20/1M | $0.06/1M | 1.05M |
| DevPass (LLM Gateway) | $0.30/1M | From$1.20/1M | $0.06/1M | — |
 APIYI | $0.30/1M | $1.20/1M | — | — |
 CrazyRouter | $0.30/1M | $1.20/1M | — | — |
| Atlas Cloud | $0.30/1M | $1.20/1M | $0.06/1M | — |
 Fireworks AI | $0.30/1M | From$1.20/1M | $0.06/1M | — |
 FastRouter | $0.30/1M | From$1.20/1M | $0.06/1M | 1M |
 Jiekou.AI | $0.30/1M | $1.20/1M | $0.06/1M | — |
 Prime Inference | $0.30/1M | $1.20/1M | — | — |
| AI/ML API | $0.30/1M | $1.20/1M | $0.06/1M | — |
 Impossibl | $0.30/1M | From$1.20/1M | $0.06/1M | — |
 Cortecs | $0.301/1M | $1.21/1M | $0.06/1M | — |
 Poe | $0.303/1M | $1.21/1M | $0.061/1M | 512K |
 Charm Hyper | $0.327/1M | $1.31/1M | $0.064/1M | — |
 CrossModel | $0.33/1M | From$1.32/1M | $0.066/1M | — |
 TensorX | $0.40/1M | $2/1M | $0.10/1M | — |
 Ofox | $0.60/1M | $2.40/1M | $0.12/1M | 1.13M |
- EmpirioLabs AIFrom$0.90
- APIMart$0.96
- CometAPIFrom$0.96
- Boundless$1.10
- Hugging FaceFrom$1.10
- Deep InfraFrom$1.10
- AIHubMix$1.15
- Venice AI$1.20
- OpenCode$1.20
- OrcaRouter$1.20
- Vercel AI Gateway$1.20
- SiliconFlow$1.20
Specs
- Type
- Text
- Maker
- MiniMax
- Inputs
- Image, Text, Video
- Outputs
- Text
- Context
- 1M≈ 1500 pages of text
- Max output
- 512K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling, Vision
- Released
- Jun 2, 2026
- License
- minimax-communitycommercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 427B
- Arena score
- 1482WebDev
- Monthly searches
- 26K
Alternatives to MiniMax-M3
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| MiniMax-M3this model | $0.90/1M | 1M | 1482 | 34 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| GLM-5.2 | $1.80/1M | 1M | 1604 | 44 |
| Grok Build 0.1 | $1.60/1M | 256K | — | 18 |
More from MiniMax
MiniMax H3MiniMax$0.02/secMiniMax H3 MaxMiniMax$0.048/secMiniMax-M3.1-FlashMiniMax$0.45/1M(Hailuo AI) Video 01MiniMax$0.50/videoMiniMax M2.5MiniMax$0.95/1MMiniMax H3 SingularityMiniMax$0.025/secMiniMax-M3.1-Flash-PreviewMiniMax$3.20/1MMiniMax H3 Max TurboMiniMax$0.024/secMiniMax-M3 FAQ
MiniMax charges $1.20 /1M for MiniMax-M3. The lowest price across providers is $0.90 /1M, at EmpirioLabs AI.
EmpirioLabs AI, at $0.90 /1M. 34 providers serve MiniMax-M3; the table above lists every one with its price.
MiniMax-M3 reads up to 1M tokens per request and writes up to 512K.
Yes. MiniMax-M3's weights can be downloaded from its maker's Hugging Face page, under the minimax-community license.
About 427B, as the safetensors metadata of its official Hugging Face repo states.
34 API providers serve MiniMax-M3. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us