# MiniMax M2.7

MiniMax M2.7 egy MI-modell, fejlesztője: MiniMax (nyílt súlyokkal), megjelenési dátuma: 2026-03-18. A kontextusablak mérete 204 800 token.

- Fejlesztő: MiniMax
- Id: minimaxai/minimax-m2.7
- Hírek szerint: 2026-03-24T09:52:02.000Z
- Megjelent: 2026-03-18T00:00:00.000Z
- Észlelés: 2026-09-18T05:10:18.499Z
  - [bizonyítékra mutató hivatkozás](https://huggingface.co/MiniMaxAI/MiniMax-M2.7)
- Állapot: Megjelent
- Súlyverzió: 2026-04-09
  - [bizonyítékra mutató hivatkozás](https://huggingface.co/api/models/MiniMaxAI/MiniMax-M2.7/paths-info/0a6536713b0b03f3be97494e5cf8d22f668a3164)
- Kanonikus cím: https://alexgetman.com/hu/models/minimax/minimax-m2-7-726/

## Kérdések

### Mekkora a(z) MiniMax M2.7 kontextusablaka?

A kontextusablak mérete 204 800 token.

### Nyilvánosan hozzáférhetők a(z) MiniMax M2.7 súlyai?

Igen. A súlyokat a(z) MiniMax közzéteszi.

### Mikor jelent meg a(z) MiniMax M2.7?

A megjelenés dátuma: 2026-03-18.

## Idővonal

- 2026-11-05T17:47:34.513Z · [GitHub · MiniMax-AI/minimax-code · code](https://github.com/MiniMax-AI/minimax-code/blob/3c21163c85a9684030cb147bfef48c6284fa3c46/packages/agent-modules/system-reminder/src/mcode-tools-master-reminder.ts)
> const MCODE_TOOLS_MODEL_PREFIX = 'MiniMax-M2.7';
> 
> const MCODE_TOOLS_MASTER_REMINDER = [
>   '<mcode-tools-master-reminder>',
>   'For multimodal generation and understanding, including images/photos, video, audio, music, and documents, load the mcode-tools-master skill and use mcode-tools through Bash.',
>   'Discover the relevant tools before concluding that a multimodal capability is unavailable.',
>   '</mcode-tools-master-reminder>',
> ].join('\n');
> 
> export function withMcodeToolsMasterReminder(input: {
>   reminderText: string | undefined;
>   modelID: string | undefined;
>   enabled: boolean;
> }): string | undefined {
>   if (!input.enabled || !input.modelID?.startsWith(MCODE_TOOLS_MODEL_PR
Ez a kódbeli hivatkozás nem igazol használatban lévő modellazonosítót.
- 2026-11-13T18:36:02.583Z · [GitHub search · MiniMax · pulls · anchapin/plan-coder · @anchapin](https://github.com/anchapin/plan-coder/pull/11)
> Worker: balanced tier, minimax/MiniMax-M2.7, 107041 tokens out, 60/60 steps. Brief was revised after a Goldfish review (13 findings, 2 premise Blockers, all applied) before dispatch;
- 2026-11-13T18:36:02.583Z · [GitHub search · MiniMax · pulls · anchapin/plan-coder · @anchapin](https://github.com/anchapin/plan-coder/pull/12)
> Worker: minimax/MiniMax-M2.7 (balanced tier), 15,403 tokens out, 24/60 steps, grade 83.
- 2026-11-13T18:36:02.583Z · [GitHub search · MiniMax · pulls · opencard-ai/opencard · @opencard-ai](https://github.com/opencard-ai/opencard/pull/58)
> Normal Doctor of Credit feeds plus an actual MiniMax-M2.7 provider with explicit key/fetch/deadline injection, strict response validation and secret-free errors. Live network/model use was NOT
- 2026-11-13T18:36:25.650Z · [GitHub search · MiniMax · commits · leshicorn/email-bot · @unknown](https://github.com/leshicorn/email-bot/commit/820e8c6aa70466ee24eefd5d236f35c763b214ca)
> - MiniMaxAI/MiniMax-M2.7: 15.7 s, 3 004 tokens, exactly the 3 right "important"
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · RRiboulet/my-agent-setup · @RRiboulet](https://github.com/RRiboulet/my-agent-setup/pull/138)
> `400 Model is unavailable`, and `mimo-v2.5`, `mimo-v2.5-pro`, `minimax-m2.7`
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · a2aproject/a2a-samples · @octo-patch](https://github.com/a2aproject/a2a-samples/pull/479)
> - Strips `<think>` reasoning tags from model responses (MiniMax M2.7 is a thinking model)
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · anchapin/matchline · @anchapin](https://github.com/anchapin/matchline/pull/1390)
> main agent re-queued it through the helper). Balanced MiniMax-M2.7, ~23.6k tokens out, grade 59.
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · anchapin/matchline · @anchapin](https://github.com/anchapin/matchline/pull/1391)
> Worker: minimax/MiniMax-M2.7 (balanced tier), 60/60 steps (hit cap while verifying), ~70,315 tokens out. Grade 93.
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · arcships/dim · @yyhhyyyyyy](https://github.com/arcships/dim/pull/1515)
> holds eight entries. `kimi-for-coding/k3.1-pro` sets `limit.context` to 262144; `custom-provider/MiniMax-M2.7` sets `extra_capabilities.reasoning.interleaved`, both moved from `applyLocalModelOverrides` in main's script. `aihubmix/glm-5.3-flashx` sets reasoning, tool call, metadata features
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · lightconsen/models · @john2ai](https://github.com/lightconsen/models/pull/16)
> ContactSales, no rate to carry: llama-3.1-8b-instant, llama-3.3-70b-versatile, meta-models/muse-spark-open, minimaxai/minimax-m2.7
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · xiaoY233/Chat2API · @octo-patch](https://github.com/xiaoY233/Chat2API/pull/184)
> Reason: The MiniMax built-in provider registry only listed MiniMax-M2.7 and was missing the MiniMax-M3 model entry.
- 2026-11-13T19:05:09.193Z · [GitHub search · MiniMax · commits · Lore-Hex/quill-router · @jperla](https://github.com/Lore-Hex/quill-router/commit/664e5541dd2f40274ca93378ac783395e1c3576c)
- 2026-11-13T19:05:09.193Z · [GitHub search · MiniMax · commits · flexaihq/dify-flexai · @sundar-flex](https://github.com/flexaihq/dify-flexai/commit/a7fd8bfa8c398440b54fdcc25c4d883c89f24f29)

## Bizonyítékokra mutató hivatkozások

- [GitHub search · MiniMax · commits · Lore-Hex/quill-router · @jperla](https://github.com/Lore-Hex/quill-router/commit/664e5541dd2f40274ca93378ac783395e1c3576c)
- [GitHub · MiniMax-AI/minimax-code · code](https://github.com/MiniMax-AI/minimax-code/blob/3c21163c85a9684030cb147bfef48c6284fa3c46/packages/agent-modules/system-reminder/src/mcode-tools-master-reminder.ts)
- [GitHub search · MiniMax · pulls · RRiboulet/my-agent-setup · @RRiboulet](https://github.com/RRiboulet/my-agent-setup/pull/138)
- [GitHub search · MiniMax · pulls · a2aproject/a2a-samples · @octo-patch](https://github.com/a2aproject/a2a-samples/pull/479)
- [GitHub search · MiniMax · pulls · anchapin/matchline · @anchapin](https://github.com/anchapin/matchline/pull/1390)
- [GitHub search · MiniMax · pulls · anchapin/matchline · @anchapin](https://github.com/anchapin/matchline/pull/1391)
- [GitHub search · MiniMax · pulls · anchapin/plan-coder · @anchapin](https://github.com/anchapin/plan-coder/pull/11)
- [GitHub search · MiniMax · pulls · anchapin/plan-coder · @anchapin](https://github.com/anchapin/plan-coder/pull/12)
- [GitHub search · MiniMax · pulls · arcships/dim · @yyhhyyyyyy](https://github.com/arcships/dim/pull/1515)
- [GitHub search · MiniMax · commits · flexaihq/dify-flexai · @sundar-flex](https://github.com/flexaihq/dify-flexai/commit/a7fd8bfa8c398440b54fdcc25c4d883c89f24f29)
- [GitHub search · MiniMax · commits · leshicorn/email-bot · @unknown](https://github.com/leshicorn/email-bot/commit/820e8c6aa70466ee24eefd5d236f35c763b214ca)
- [GitHub search · MiniMax · pulls · lightconsen/models · @john2ai](https://github.com/lightconsen/models/pull/16)
- [GitHub search · MiniMax · pulls · opencard-ai/opencard · @opencard-ai](https://github.com/opencard-ai/opencard/pull/58)
- [GitHub search · MiniMax · pulls · xiaoY233/Chat2API · @octo-patch](https://github.com/xiaoY233/Chat2API/pull/184)
- [review](https://huggingface.co/MiniMaxAI/MiniMax-M2.7)
- [hf-author-artifacts:MiniMaxAI](https://huggingface.co/api/models/MiniMaxAI/MiniMax-M2.7/paths-info/0a6536713b0b03f3be97494e5cf8d22f668a3164)

## Jelzések