MiniMax M3 API: pricing, base URL and quick setup

Specifications and pricing

USD per 1M tokens. Final billing depends on your API key group and metered usage.

Cheapest way to use MiniMax M3

Quick setup

curl https://a2agent.me/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-a2agent-key" \
  -d '{
    "model": "minimax-m3",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

Using it from a coding client

Suits agent frameworks that plan, call tools and re-read state on every turn. The 1M window absorbs long transcripts.

• Run it in Claude Code
• Run it in Codex CLI

How it compares within its family

These comparisons use catalog context limits, tags and reference rates, not independent quality benchmarks. Rates can change. Check current pricing above and test your workload; a higher price or a larger context window does not establish better results.

M3 is the agent-tagged MiniMax model and lists at $0.30 per million input tokens and $1.20 output. M3.1 Flash, the other MiniMax model sold here, lists at exactly half that: $0.15 and $0.60. Both reach 1M tokens, so context does not separate them. The tags do: M3 carries agent, M3.1 Flash carries coding and vision. Keep tool loops, planning and orchestration on M3 if they already work there, and try M3.1 Flash on the same tasks to see whether the lower rate holds up. The catalog data says nothing about output quality, so the comparison has to come from your own prompts. Total cost still depends on usage, retries included.

Other models on this platform

• MiniMax M2.51M
• MiniMax M2.7200K
• MiniMax M3.1 Flash1M

Questions