# MiniMax-M3 API pricing

The official API price of MiniMax-M3 is $0.3 per 1M input tokens and $1.2 per 1M output tokens (as of 2026-11-12). Context window: 1M tokens, up to 524K output tokens per request. 54 providers sell it. The lowest is Vultr: $0.2 input, $0.9 output.

- Type: Text
- Context: 1M
- Max output: 524K
- Released: 2026-06-01
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [MiniMax (minimax.io)](https://platform.minimax.io/docs/guides/quickstart) | MiniMax-M3 | $0.3 | $1.2 | $0.06 | Official, Tiered pricing |
| [Vultr](https://api.vultrinference.com/) | minimax-m3 | $0.2 | $0.9 | — | Lowest |
| [EmpirioLabs AI](https://docs.empiriolabs.ai) | minimax-m3 | $0.225 | $0.9 | $0.045 | Tiered pricing |
| [Ambient](https://ambient.xyz) | minimax/minimax-m3 | $0.23 | $0.96 | $0.05 |  |
| [NanoGPT](https://docs.nano-gpt.com) | minimax/minimax-m3 | $0.23 | $0.96 | $0.05 |  |
| [NanoGPT](https://docs.nano-gpt.com) | minimax/minimax-m3:thinking | $0.23 | $0.96 | $0.05 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | MiniMaxAI/MiniMax-M3 | $0.23 | $0.96 | $0.05 |  |
| [Boundless](https://inference.boundless.network/models) | minimax-m3 | $0.28 | $1.1 | $0.056 |  |
| [Deep Infra](https://deepinfra.com/models) | MiniMaxAI/MiniMax-M3 | $0.28 | $1.1 | $0.056 |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | minimax-m3 | $0.28 | $1.1 | $0.056 |  |
| [LLM Gateway](https://llmgateway.io/docs) | deepinfra/minimax-m3 | $0.28 | $1.1 | $0.056 |  |
| [AIHubMix](https://docs.aihubmix.com) | minimax-m3 | $0.288 | $1.152 | — |  |
| [IteraCompute](https://iteracompute.com/docs.html) | minimax/minimax-m3 | $0.3 | $1.19 | $0.05 |  |
| [Abacus](https://abacus.ai/help/api) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | — |  |
| [ClinePass](https://docs.cline.bot/getting-started/clinepass) | cline-pass/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [CommandCode](https://commandcode.ai/docs/provider) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Eden AI](https://docs.edenai.co) | minimax/MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Fireworks AI](https://fireworks.ai/docs/) | accounts/fireworks/models/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Fireworks AI](https://fireworks.ai/docs/) | accounts/fireworks/routers/minimax-latest | $0.3 | $1.2 | $0.06 |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | — |  |
| [Inco](https://platform.inco.ai/docs) | minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Jalapeno Cloud](https://www.jalapeno-cloud.ai/docs/) | MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Kilo Gateway](https://kilo.ai) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [LLM Gateway](https://llmgateway.io/docs) | tencent/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Modular](https://docs.modular.com/models) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Nebius Token Factory](https://docs.tokenfactory.nebius.com/) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 | Tiered pricing |
| [OpenCode](https://opencode.ai/v2/docs/console/models/) | minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [OpenCode Go](https://opencode.ai/v2/docs/console/go/) | minimax-m3 | $0.3 | $1.2 | $0.06 | Tiered pricing |
| [OpenRouter](https://openrouter.ai/models) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [OrcaRouter](https://docs.orcarouter.ai) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [SiliconFlow](https://cloud.siliconflow.com/models) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Standard Compute](https://docs.standardcompute.com/models) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | minimax/MiniMax-M3 | $0.3 | $1.2 | $0.06 | Tiered pricing |
| [Together AI](https://docs.together.ai/docs/serverless-models) | MiniMaxAI/MiniMax-M3 | $0.3 | $1.2 | $0.06 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 |  |
| [ZenMux](https://docs.zenmux.ai) | minimax/minimax-m3 | $0.3 | $1.2 | $0.06 | Tiered pricing |
| [Charm Hyper](https://hyper.charm.land) | minimax-m3 | $0.32664 | $1.30656 | $0.064239 |  |
| [CrossModel](https://www.crossmodel.ai/docs) | minimax/minimax-m3 | $0.33 | $1.32 | $0.066 | Tiered pricing |
| [Wally](https://docs.runanywhere.ai/wally-cloud/api) | minimax-m3 | $0.33 | $1.32 | $0.066 |  |
| [Kenari](https://kenari.id/docs) | minimax-m3 | $0.36 | $1.428571 | $0.068571 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | minimax-m3@eu | $0.4 | $2 | $0.1 |  |
| [TensorX](https://docs.tensorx.ai/) | minimax/minimax-m3 | $0.4 | $2 | $0.1 |  |
| [GMI Cloud](https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference) | MiniMaxAI/MiniMax-M3 | $0.6 | $2.4 | $0.12 | Tiered pricing |
| [Inco](https://platform.inco.ai/docs) | minimax-m3:fast | $0.6 | $2.4 | $0.12 |  |
| [LLM Gateway](https://llmgateway.io/docs) | minimax/minimax-m3 | $0.6 | $2.4 | $0.12 |  |
| [Ofox](https://ofox.ai/docs) | minimax/minimax-m3 | $0.6 | $2.4 | $0.12 |  |
| [Ollama Cloud](https://docs.ollama.com/cloud) | minimax-m3 | $0.6 | $2.4 | $0.12 |  |
| [Opper](https://opper.ai/models) | minimax-m3 | $0.6 | $2.4 | $0.12 | Tiered pricing |
| [SambaNova](https://docs.sambanova.ai/cloud/docs/get-started/supported-models) | MiniMax-M3 | $0.6 | $2.4 | $0.06 |  |
| [302.AI](https://doc.302.ai) | MiniMax-M3 | $0.72 | $2.88 | $0.144 | Tiered pricing |
| [Vancine](https://vancine.com/docs) | MiniMax-M3 | $0.24 | $0.96 | $0.048 | Deprecated |
| [Lilac](https://docs.getlilac.com/inference/models) | minimaxai/minimax-m3 | $0.28 | $1.1 | $0.05 | Deprecated |
| [Wafer](https://docs.wafer.ai/wafer-pass) | MiniMax-M3 | $0.33 | $1.32 | $0.07 | Tiered pricing, Deprecated |
| [Synthetic](https://synthetic.new/pricing) | hf:MiniMaxAI/MiniMax-M3 | $0.6 | $1.2 | $0.6 | Deprecated |
| [OpenCode](https://opencode.ai/v2/docs/console/models/) | minimax-m3-free | $0 | $0 | $0 | Deprecated |
| [SCNet Token Plan](https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html) | MiniMax-M3 | $0 | $0 | $0 |  |
| [Volcengine Ark Coding Plan](https://www.volcengine.com/docs/82379/1928261) | minimax-m3 | $0 | $0 | $0 | Deprecated |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/minimax/minimax-m3/