Post-Cutoff
Search For AI agents

MiniMaxMiniMax-M familyCurrentReasoning modelReleased 18 Mar 2026

MiniMax-M2.7

Budget agentic coding model with 204.8K context; good for self-hosting (SGLang) or cheap API use.

Model idMiniMax-M2.7

Price$0.30 in, $1.20 out per 1M tokens

Checked29 September 2026

No published training cutoff

At least1,905events since its release on 18 March 2026

85 historic, 435 major. 240 days of news.

MiniMax doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

5 ways to use MiniMax-M2.7, with the model id each provider expects.

Providers, model ids, endpoints and docs for MiniMax-M2.7
ProviderModel idEndpointDocs
MiniMax API (Anthropic format) MiniMax-M2.7 https://api.minimax.io/anthropic platform.minimax.io
MiniMax API (OpenAI format) MiniMax-M2.7 https://api.minimax.io/v1 platform.minimax.io
MiniMax API (fast) MiniMax-M2.7-highspeed https://api.minimax.io/v1 platform.minimax.io
OpenRouter minimax/minimax-m2.7 openrouter.ai
Hugging Face huggingface.co

Pricing

Prices for MiniMax-M2.7
Input$0.30 per 1M tokens
Output$1.20 per 1M tokens
Cache read$0.06 per 1M tokens
Cache write$0.375 per 1M tokens

As published: “per 1M tokens (USD); MiniMax-M2.7-highspeed: 0.6 / 2.4”.

Source: platform.minimax.io, checked 29 September 2026.

Specs

Input
Text
Output
Text
Context window
204,800 tokens
Max output
Not published
Open weights
Yes
Licence
other (MiniMax license, see HF)
Training cutoff
Not published
Released
18 March 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Participates in its own evolution

    MiniMax calls it its first model deeply participating in its own development (‘recursive self-improvement’).

    Source: huggingface.co

  • Agent harness building

    Builds complex agent harnesses using Agent Teams, Skills and dynamic tool search; aimed at professional office delivery.

    Source: huggingface.co

Notes

Text-only predecessor of M3, still a current API model; highspeed variant ~100 tok/s vs ~60. M2.5/M2.1/M2 are legacy (same $0.3/$1.2 price).

curl https://api.minimax.io/v1/chat/completions \
 -H "Authorization: Bearer $MINIMAX_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"MiniMax-M2.7","messages":[{"role":"user","content":"Hello"}]}'

Sources: https://platform.minimax.io/docs/guides/models-intro · https://platform.minimax.io/docs/guides/pricing-paygo · https://huggingface.co/MiniMaxAI/MiniMax-M2.7