Kyma APIKyma API
MiniMax

MiniMax

MiniMax M2.7

#7 on Kyma

MiniMax M2.7 is a text-only language model optimized for agentic workflows, coding, and debugging. Reach for it when you need reliable tool use and reasoning at a balanced cost tier.

Modalities

Text → Text

Below release

None reported

Weights

Published

MiniMaxAI/MiniMax-M2.7

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#22/71

$0.405

output $1.62

median $1.013 · best $0.0494

Price · output#22/70

$1.62

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#1/70

100%

147 observations since 2026-05-02

median 96.5% · best 100.0%

Throughput#23/66

52 tok/s

probe median, one fixed prompt

median 36.3 tok/s · best 377.8 tok/s

Response time#59/66

5.52 s

probe median, to a complete answer

median 2.73 s · best 0.84 s

Context

205K

max output 32,768

published by MiniMax, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#7

of 100 active models

Tokens served

119.8M

all-time

Platform share

2.7%

of all tokens

Tokens · last 15 daysSep 22 → Oct 6

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.405 /1M input$1.62 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.49/mo
Production1,000 req/day · 2K in / 500 out
~$48.60/mo
Scale20,000 req/day · 2K in / 500 out
~$972/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$48.60

$1.62 / day on MiniMax M2.7

Same workload on:

MiniMax M2.5$48.60≈
MiniMax M3$48.60≈

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

When to use MiniMax M2.7

Updated 2026-07-29

Where this model earns its cost — and where it doesn't.

MiniMax M2.7 is a frontier-tier language model built by MiniMax for agentic productivity. It accepts text input and returns text output, with native support for tool calling, structured outputs, and explicit reasoning steps. It operates with a 204,800-token context window and a maximum output length of 32,768 tokens.

On Kyma, the model runs on an OpenAI-compatible endpoint at medium generation speed, routing automatically through failover paths if a serving instance degrades. Responses include exact token costs in the usage.cost field and identify the executed model via the X-Kyma-Model header.

The model does not support vision inputs or prompt caching. If your workflow relies on image analysis or requires cached prefix discounts, you will need to route elsewhere or structure prompts differently.

Agentic Workflow Orchestration

Handles multi-step tool calls and state tracking for autonomous agents.

Code Generation and Debugging

Writes, reviews, and fixes code across multiple languages with structured reasoning.

Productivity and Content Drafting

Generates long-form text and organizes complex information within a large context window.

Structured Data Extraction

Outputs strictly formatted JSON or XML for downstream parsing and API integration.

Not ideal for: Do not use this model for tasks requiring image understanding, multimodal input, or prompt caching discounts.

How it compares

Against the peers people actually weigh it against.

SpecMiniMax M2.7MiniMax M2.5MiniMax M3
Input /1M$0.405$0.405$0.405
Output /1M$1.62$1.62$1.62
Context205K197K1M
ToolsYesYesYes
ReasoningYesYesYes
Throughput52 tok/s74 tok/s35 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers MiniMax M2.7. No card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.7",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.7",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of MiniMax M2.7?

MiniMax M2.7 has a 205K-token context window — roughly 301 pages of text in a single request.

How much does the MiniMax M2.7 API cost?

$0.405 per 1M input tokens and $1.62 per 1M output tokens. No subscription; you pay only for what you use.

Does MiniMax M2.7 support function calling?

Yes — MiniMax M2.7 supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for MiniMax M2.7 publicly available?

Yes. MiniMax publishes MiniMax M2.7's weights as MiniMaxAI/MiniMax-M2.7, so you can download and run the model yourself (https://huggingface.co/MiniMaxAI/MiniMax-M2.7, read 2026-08-14). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is MiniMax M2.7 ever served below the precision its creator released it at?

Not as far as Kyma can see. MiniMax M2.7 was released by MiniMax at fp8 + bf16 (https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/config.json, read 2026-08-14), and no route serving it here reports a format below that, as checked on 2026-09-21. Read that as the absence of a claim rather than as a guarantee: a route publishes its precision only where it chooses to, and most state nothing either way.

How do I use MiniMax M2.7?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to minimax-m2.7. Signing up is free and includes $0.50 of credit on the free tier, which covers this model — no card required.

Does this model support image inputs?

No, MiniMax M2.7 is text-only. Route to a multimodal model if your workflow requires vision.

Can I use prompt caching with this model?

No, the model does not support caching. Prefixes will be billed at the standard input rate.

How do I track costs per request?

Every response includes the exact token cost in the usage.cost field, and the X-Kyma-Model header confirms which model executed the request.

Start with $0.50 free credit on the free tier — no card required.Create account →

More models by MiniMax

ModelContextInputOutput
MiniMaxMiniMax M31M$0.405$1.62
MiniMaxMiniMax M2.5197K$0.405$1.62
MiniMaxMiniMax Speech Turbo—$0.04 / 1K char
MiniMaxMiniMax Speech HD—$0.07 / 1K char
MiniMaxMiniMax Image 01—$0.005 / image