Post-Cutoff
Search For AI agents

MiniMaxMiniMax-M familyCurrentReasoning modelReleased 1 Jun 2026

MiniMax-M3

Low-cost 1M-context multimodal coding/agent model; Anthropic-SDK-first API, open weights.

Model idMiniMax-M3

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

Checked29 September 2026

No published training cutoff

At least1,826events since its release on 1 June 2026

82 historic, 419 major. 165 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

4 ways to use MiniMax-M3, with the model id each provider expects.

Providers, model ids, endpoints and docs for MiniMax-M3
ProviderModel idEndpointDocs
MiniMax API (Anthropic format) MiniMax-M3 https://api.minimax.io/anthropic platform.minimax.io
MiniMax API (OpenAI format) MiniMax-M3 https://api.minimax.io/v1 platform.minimax.io
OpenRouter minimax/minimax-m3 openrouter.ai
Hugging Face huggingface.co

Pricing

Prices for MiniMax-M3
Input$0.30 per 1M tokens
Output$1.20 per 1M tokens
Cache read$0.06 per 1M tokens

As published: “per 1M tokens (USD), standard tier, input <=512K (after permanent 50% discount); >512K input: 0.60/2.40/0.12. Priority tier 1.5x”.

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

Specs

Input
Text, images and video
Output
Text
Context window
1,000,000 tokens
Max output
Not published
Open weights
Yes
Licence
MiniMax Community License
Training cutoff
Not published
Released
1 June 2026
Status
Current
Type
Reasoning model

What stands out

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

  • MiniMax Sparse Attention (MSA)

    New sparse attention for million-token contexts: 9x prefill and 15x decode speed-up vs M2 at 1M context, ~1/20 per-token compute.

    Source: huggingface.co

  • Native multimodality from step one

    Mixed text/image/video training from the start of pre-training (~428B total / ~23B active).

    Source: huggingface.co

  • Three reasoning modes

    thinking parameter selects among three reasoning modes; interleaved thinking with tool use.

    Source: huggingface.co

Notes

MiniMax flagship LLM. OpenAI-format responses include <think> content that must be preserved across turns. MiniMax-M3.1-Flash-Preview (1M, tunable thinking) exists but only via Token Plan/MiniMax Code.

curl https://api.minimax.io/anthropic/v1/messages \
 -H "x-api-key: $MINIMAX_API_KEY" -H "anthropic-version: 2023-06-01" -H "Content-Type: application/json" \
 -d '{"model":"MiniMax-M3","max_tokens":4096,"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-M3

Not yet checked against an official source: Max output and knowledge cutoff not verified.