MiniMax

MiniMax-M2.5-highspeed

DeprecatedOpen weights205K contextReasoning

Summary

MiniMax-M2.5-highspeed is an open-weight language model from MiniMax, released on 13 Feb 2026. It accepts text and generates text, with a 205K-token context window and up to 131K output tokens per response. MiniMax has deprecated this model.

High-speed MiniMax model for low-latency coding and agent workflows

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMiniMax
Release date13 Feb 2026 [models.dev]
StatusDeprecated [models.dev]
WeightsOpen weights [models.dev]
Context window205K (204,800 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoff1 Jan 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]

MiniMax-M2.5-highspeed API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of MiniMax-M2.5-highspeed?

MiniMax-M2.5-highspeed has a context window of 204,800 tokens (205K) and can generate up to 131,072 tokens in a single response, according to models.dev.

Is MiniMax-M2.5-highspeed open source?

MiniMax-M2.5-highspeed is an open-weight model. Check the license terms before commercial use.

When was MiniMax-M2.5-highspeed released?

MiniMax released MiniMax-M2.5-highspeed on 13 Feb 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GLM-5Zhipu AI (Z.ai)12 Feb 2026205K$0.95$2.55Open
GLM-4.7-FlashZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open
Qwen3.5 397B-A17BAlibaba (Qwen)15 Feb 2026262K$0.45$3Open
Qwen3 Max ThinkingAlibaba (Qwen)9 Feb 2026262K–––
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
Kimi K2.5Moonshot AI27 Jan 2026262K$0.45$2.25Open

Change history

  • No longer listed on vercel
  • Knowledge cutoff changed from none to 1 Jan 2025
  • Status changed from active to deprecated
  • No longer listed on minimax
  • No longer listed on novita-ai
  • minimax price changed: input $0.60 → $0.60, output $2.40 → $2.40 per 1M tokens

Sources