What fundamentally changed between the 2.5 and 2.7 generations?

Three capabilities that didn't exist in M2.5: native multi-agent coordination (no external orchestration code), dynamic tool search (tools found at runtime rather than declared upfront), and enterprise office automation (document analysis, structured data, reporting).

How does runtime tool discovery work?

Instead of receiving a fixed tool manifest in the prompt, MiniMax M2.7 High Speed evaluates the evolving task state and identifies relevant tools. It invokes them without prior declaration, expanding the model's effective action space over long sessions.

Does switching from the previous highspeed variant require code changes?

Only the model identifier string. Update to `minimax/minimax-m2.7-highspeed` in your API calls. The tool-calling format, API surface, and AI Gateway configuration stay the same.

Can MiniMax M2.7 High Speed coordinate agents built on different model families?

Yes. The orchestration logic is native to the M2.7 architecture, but the agents it coordinates can run any model. Coordination fidelity is strongest when MiniMax M2.7 High Speed serves as the orchestrating agent.

Is throughput the same as the prior highspeed generation?

Both target comparable throughput (see live metrics on this page). The improvement is capability breadth per token, not token velocity.

When does the standard-rate M2.7 make more sense?

When nobody is waiting on the output. Background batch processing, scheduled overnight jobs, and any pipeline where wall-clock duration doesn't affect user experience or business outcomes.

MiniMax

MiniMax M2.7 High Speed

MiniMax M2.7 High Speed is the throughput-optimized variant of M2.7. It supports a context window of 204.8K tokens and a max output of 131.1K tokens.

View API reference

Input and output price: Input $0.60, Output $2.40, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'minimax/minimax-m2.7-highspeed',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out MiniMax M2.7 High Speed by MiniMax. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

MiniMax M2.7 High Speed

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

MiniMax

Legal:Terms•Privacy

205K

131K

$0.60/M

$2.40/M

Read$0.06/M

Write$0.38/M

—

03/18/2026

Getting started

Call MiniMax M2.7 High Speed through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'minimax/minimax-m2.7-highspeed',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same MiniMax M2.7 High Speed request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'minimax/minimax-m2.7-highspeed',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `minimax/minimax-m2.7-highspeed`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. MiniMax M2.7 High Speed supports up to `131,100` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 205K-token context window

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'minimax/minimax-m2.7-highspeed',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['minimax'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'minimax/minimax-m2.7-highspeed',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'minimax/minimax-m2.7-highspeed',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by MiniMax

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

minimax/minimax-m3

0.8 s

277 tps

$0.26/M

$1.02/M

Read$0.06/M

—

05/31/2026

minimax/minimax-m2.7

205K

1.0 s

61 tps

$0.30/M+1 more

$1.20/M+1 more

Read$0.06/M

Write$0.38/M

—

03/18/2026

minimax/minimax-m2.5

0.6 s

82 tps

$0.27/M+1 more

$0.95/M+1 more

Read$0.03/M

Write$0.38/M

—

02/12/2026

minimax/minimax-m2.5-highspeed

205K

0.9 s

82 tps

$0.60/M

$2.40/M

Read$0.03/M

Write$0.38/M

—

02/12/2026

minimax/minimax-m2.1

205K

0.8 s

106 tps

$0.30/M

$1.20/M

Read$0.03/M

Write$0.38/M

—

12/23/2025

minimax/minimax-m2

205K

0.8 s

82 tps

$0.30/M

$1.20/M

Read$0.03/M

Write$0.38/M

—

10/27/2025

Copy link to headingAbout MiniMax M2.7 High Speed

Three architectural capabilities separate the 2.7 generation from earlier MiniMax releases. MiniMax M2.7 High Speed delivers all three at accelerated inference.

1. Agent-to-agent orchestration without middleware. Earlier MiniMax models operated as isolated workers. Coordinating them required external scaffolding: custom code to pass context, manage handoffs, and track dependencies. MiniMax M2.7 High Speed internalizes that orchestration layer. It manages context propagation, dependency resolution, and agent handoffs natively. In parallel architectures, compressing per-agent token generation shortens the critical path.

2. Runtime tool discovery. Prior generations consumed a static tool manifest declared at prompt time. MiniMax M2.7 High Speed breaks that constraint: it identifies, evaluates, and invokes tools dynamically as a task unfolds. For long-horizon automation where required actions can't be predicted upfront, this reduces the need to pre-enumerate every tool interaction.

3. Enterprise document processing. Structured data extraction, report synthesis, spreadsheet analysis, and document transformation join the capability set. A single endpoint now serves both engineering automation and business-process work, reducing the number of specialized models you manage.

Throughput remains high (see live metrics on this page). The generational leap is in what the model accomplishes per token, not how many tokens it produces.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: MiniMax M2.7 High Speed lists at roughly 2x the standard M2.7 input and output rates on many providers. AI Gateway's per-request cost tracking helps you quantify whether the throughput gain justifies the expense for your workload.
Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use MiniMax M2.7 High Speed

Best for

Parallel agent architectures: Per-agent token velocity directly compresses end-to-end task completion
Autonomous tool discovery: Workflows that must locate and invoke unfamiliar tools as subtasks emerge during execution
Unified engineering and business: Pipelines that need code generation and document processing from one endpoint
Native orchestration replacement: Organizations replacing external middleware with a model that coordinates agents natively

Consider alternatives when

Independent agents: Your agents never exchange context, so an earlier highspeed variant handles isolated coding at lower cost
Batch jobs without pressure: Standard M2.7 produces identical results at the baseline rate
Budget ceiling exceeded: The 2x per-token premium exceeds your budget regardless of latency benefit

Copy link to headingConclusion

MiniMax M2.7 High Speed adds agent orchestration, runtime tool discovery, and enterprise document work while sustaining the throughput that makes long-running, multi-agent sessions viable. It pairs the full M2.7 capability set with high-throughput inference for teams whose workloads have outgrown single-agent patterns.

Copy link to headingFrequently Asked Questions

What fundamentally changed between the 2.5 and 2.7 generations?
Three capabilities that didn't exist in M2.5: native multi-agent coordination (no external orchestration code), dynamic tool search (tools found at runtime rather than declared upfront), and enterprise office automation (document analysis, structured data, reporting).
How does runtime tool discovery work?
Instead of receiving a fixed tool manifest in the prompt, MiniMax M2.7 High Speed evaluates the evolving task state and identifies relevant tools. It invokes them without prior declaration, expanding the model's effective action space over long sessions.
Does switching from the previous highspeed variant require code changes?
Only the model identifier string. Update to minimax/minimax-m2.7-highspeed in your API calls. The tool-calling format, API surface, and AI Gateway configuration stay the same.
Can MiniMax M2.7 High Speed coordinate agents built on different model families?
Yes. The orchestration logic is native to the M2.7 architecture, but the agents it coordinates can run any model. Coordination fidelity is strongest when MiniMax M2.7 High Speed serves as the orchestrating agent.
Is throughput the same as the prior highspeed generation?
Both target comparable throughput (see live metrics on this page). The improvement is capability breadth per token, not token velocity.
When does the standard-rate M2.7 make more sense?
When nobody is waiting on the output. Background batch processing, scheduled overnight jobs, and any pipeline where wall-clock duration doesn't affect user experience or business outcomes.

Your use is subject to MiniMax's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

MiniMax M2.7 High Speed

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Tool calling

Copy link to headingMore models by MiniMax

Copy link to headingAbout MiniMax M2.7 High Speed

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use MiniMax M2.7 High Speed

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions