MiniMax

M3 API

Built for long-horizon coding, tool use, and multi-turn production collaboration, extending beyond MiniMax M2.7 with multimodal inputs while keeping a 1M-token context window. Compared with Claude, Gemini, and GLM-5.2 long-context agent models, it is better for putting text, image, and video materials into one workflow.

  • Reasoning
  • Tool use
  • Function calling
  • Structured output
  • Long context
Use in ConsoleMiniMax-M3

USD

Pricing

default
Standard Rate
Input$1.26/1M tokensCompletion Price$5.04/1M tokensCache Read$0.252/1M tokens

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "MiniMax-M3",
    "messages": [
        {
            "role": "user",
            "content": "What model are you"
        }
    ]
}'

MiniMax

Related models

FAQ

Frequently asked questions

What is M3 best suited for?

M3 is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is M3 priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call M3?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with M3

Use in Console
TokenHot

The frontier intelligence gateway. One API. 127 models. 0.2s latency. Pay only for what you use.

All systems normal · 99.997% uptime

Company

© 2026 TokenHot Inc. — Built for builders.