For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
WebsiteModelsPricingGet Started
DocumentationAPI Reference
DocumentationAPI Reference
  • Overview
    • Welcome
    • Getting Started
    • Authentication
    • Concepts
  • Platform
    • Models and Pricing
    • Billing and Credits
    • Limits and API Keys
    • Account Usage API
    • Generation Templates
    • GPU Cloud
    • Hosted Agents
    • OpenAI and Anthropic Compatibility
    • Integrations
  • Providers and Models
    • All providers
      • MiniMax overview
      • MiniMax M2.7
      • MiniMax M2.7 Highspeed
      • MiniMax M3
  • Reference
    • API Reference Overview
    • AI Agent Access
    • Support
    • Changelog
Logo
WebsiteModelsPricingGet Started
On this page
  • At a glance
  • Pricing
  • Example request
  • Parameters
  • Notes
Providers and ModelsMiniMax

MiniMax M3

Was this page helpful?
Previous

Mistral AI

Next
Built with
MiniMax M3
MiniMax · Text Generation
POST /v1/chat/completions

MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input.

At a glance

FieldValue
Model idminimax-m3
Input modalitiesText, Image, Video
Output modalitiesText
Context window524K
Weight precision-
Max output tokens524,288
RegionSingapore
Featuresreasoning, vision, video, function_calling, cache, long_context
Native inferenceNo
NewYes
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages

Pricing

ChargeSpecRate
Inputper 1M prompt tokens<=512K $0.30 (was $0.60); >512K $1.20
Outputper 1M generated tokens<=512K $1.20 (was $2.40); >512K $4.80
Implicit cache readper 1M cached input tokens<=512K $0.06 (was $0.12); >512K $0.24

Example request

$curl https://api.empiriolabs.ai/v1/chat/completions \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "minimax-m3", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno1Controls randomness. Lower values are more deterministic; higher values are more exploratory. · Range: 0 – 2
top_pnumberno0.95Controls nucleus sampling by limiting generation to the most likely token mass. · Range: 0 – 1
max_completion_tokensintegerno4096Maximum generated tokens, including reasoning tokens when thinking is enabled. · Range: 1 – 524288
stoparrayno—Optional stop sequence or list of stop sequences.
enable_thinkingbooleannotrueEnable adaptive model thinking before answering. Set false to request a direct answer without a reasoning phase.
toolsarrayno—OpenAI-compatible tool definitions for function calling.
tool_choiceobjectno—Optional OpenAI-compatible tool_choice value.

Notes

Text, image, and video input with text output. Thinking defaults to adaptive and can be disabled. Pricing is based on input tokens including cache hits: <=512K uses the discounted standard tier, while >512K uses the high-context tier. Current standard route supports up to 524K tokens. 1M context is rolling out.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/minimax-m3.