How does MiniMax-M2.7 score on benchmarks?

Recorded results for MiniMax-M2.7: aa_intelligence_index 39.2; arena_text 83.4. Benchmark positions are a coarse filter only — run your own prompts against the candidate models before you commit, because ranking shifts with task shape and prompt style.

How much does prompt caching save on MiniMax-M2.7?

Prompt caching on MiniMax-M2.7 bills cached input at $0.06 per 1,000,000 token instead of $0.3 per 1,000,000 token for standard input. The saving applies to the cached prefix only; the rest of the request is billed normally.

What should you evaluate before moving production traffic to MiniMax-M2.7?

Before switching production traffic to MiniMax-M2.7, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

When was MiniMax-M2.7 released, and is it still maintained?

MiniMax-M2.7 was released on 2026-03-18. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

How do you get a cache hit on MiniMax-M2.7?

A cache hit on MiniMax-M2.7 requires an identical prompt prefix across requests. Put your stable instructions and reference material at the start of the prompt, keep them byte-identical, and let the changing part follow. Cached reads are then billed at the cache rate rather than the input rate.

Model detail

MiniMax-M2.7

Provided by Minimax

Pay-as-you-go

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

Model specs

Model ID: MiniMax-M2.7

Context length: 204.8K
Max output: 131.072K
I/O modalities
Released: 2026-03

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$0.3000 /1M Tokens

Completion

$1.2000 /1M Tokens

Cache read

$0.0600 /1M Tokens

Cache creation

$0.3750 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Next-generation large language model designed for autonomous

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.

What should you check before using it?

204,800 context, 131,072 output tokens

Model type: text. Verify supported features and quotas with the provider documentation. Released 2026-03-18.

Why use it through MixRoute?

MiniMax-M2.7 keeps its 204,800-token context on one route

The full 204,800-token context stays reachable on the same route. MixRoute serves MiniMax-M2.7 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID MiniMax-M2.7 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

MiniMax-M2.7 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

MiniMax-M2.7 can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

MiniMax-M2.7 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

MiniMax-M2.7 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

OpenAI SDK

Call MiniMax-M2.7 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 204.8K

Output tokens Max per request 131.072K

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

Yes. MiniMax-M2.7 is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to MiniMax-M2.7. Keep your current request and response handling.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

MiniMax-M2.7

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs