MiniMax M2.1
MiniMax M2.1 is MiniMax's second-generation model, focused on coding accuracy, tool use, instruction following, and long-horizon planning. It supports a context window of 204.8K tokens and a max output of 131.1K tokens per request.
View API reference- Input and output price
- Prices from: Input $0.30, Output $1.20, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'minimax/minimax-m2.1', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out MiniMax M2.1 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 M2.1
MiniMax M2.1
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call MiniMax M2.1 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'minimax/minimax-m2.1', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same MiniMax M2.1 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'minimax/minimax-m2.1', 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-m2.1. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. MiniMax M2.1 supports up to 131,072 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'minimax/minimax-m2.1', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['minimax', 'novita'], }, }, });
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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'minimax/minimax-m2.1', 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.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'minimax/minimax-m2.1', 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 |
|---|
| 1M | 0.9 s | 200 tps | $0.26/M | $1.02/M | Read$0.06/M | — | +2 |   +2 | 05/31/2026 | |||||
| 205K | 1.4 s | 47 tps | $0.30/M+1 more | $1.20/M+1 more | Read$0.06/M Write$0.38/M | — |  | 03/18/2026 | ||||||
| 205K | 1.1 s | 51 tps | $0.60/M | $2.40/M | Read$0.06/M Write$0.38/M | — | | 03/18/2026 | ||||||
| 1M | 0.4 s | 93 tps | $0.27/M+1 more | $0.95/M+1 more | Read$0.03/M Write$0.38/M | — |   +1 | 02/12/2026 | ||||||
| 205K | 1.1 s | 66 tps | $0.60/M | $2.40/M | Read$0.03/M Write$0.38/M | — | | 02/12/2026 | ||||||
| 205K | 0.9 s | 74 tps | $0.30/M | $1.20/M | Read$0.03/M Write$0.38/M | — | | 10/27/2025 |
Copy link to headingAbout MiniMax M2.1
Released on December 23, 2025, MiniMax M2.1 ships alongside a speed-optimized sibling (M2.1 Lightning). Standard MiniMax M2.1 targets reliability gaps that kept M2 out of serious engineering pipelines.
M2 could write passable code, but outputs grew inconsistent on harder assignments. Instruction sequences with four or five chained tool invocations sometimes arrived reordered or incomplete. MiniMax M2.1 addresses both issues through targeted training improvements across Go, C++, JavaScript, C#, TypeScript, Rust, Java, Kotlin, and Objective-C. The result is cleaner output on refactoring, feature scaffolding, bug isolation, and automated review.
Interleaved Thinking (alternating reasoning steps with action steps) debuted with the 2.1 generation. It gives the model a structured way to plan before executing multi-part instructions. For asynchronous workloads like CI-triggered reviews, nightly code audits, or batch refactoring queues, standard MiniMax M2.1 delivers identical output quality at the baseline rate.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Teams whose requests run asynchronously (background jobs, scheduled pipelines, queued reviews) gain nothing from a throughput premium. Standard MiniMax M2.1 at the baseline rate is the right choice for those patterns.
- Zero Data Retention: Zero Data Retention is available for this model. It 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 M2.1
Best for
- Polyglot codebases: Projects using Go, C++, JavaScript, C#, TypeScript, Rust, Java, Kotlin, or Objective-C
- Asynchronous engineering pipelines: CI review bots, nightly audit scripts, and queued refactoring
- Long tool-call chains: Sequences of four or more steps that demand sequential fidelity
- Upgrading from M2: Teams that need measurably better code without changing the cost envelope
Consider alternatives when
- Real-time latency sensitivity: End users watch response tokens arrive live and perceive delays, so use M2.1 Lightning
- Architectural planning needed: M2.5 introduced plan-then-code capability
- Vision input required: M2.1 is text-only; route image-bearing requests to a multimodal model instead
Copy link to headingConclusion
MiniMax M2.1 fixed the rough edges that kept M2 out of production engineering workflows. It delivers cleaner multilingual output, reliable multi-step execution, and Interleaved Thinking at the standard rate. It serves as the foundation of MiniMax's second generation for teams that prioritize correctness over velocity.
Copy link to headingFrequently Asked Questions
What specific programming tasks improved from M2 to MiniMax M2.1?
Refactoring accuracy, feature scaffolding structure, bug-fix precision, and automated code-review adherence all improved. The gains show most on multi-file tasks that require sustained instruction fidelity.
Does MiniMax M2.1 support Interleaved Thinking?
Yes. The 2.1 generation introduced this capability, letting the model alternate between reasoning and action during complex instruction sequences.
How does MiniMax M2.1 handle a five-step tool-call chain?
MiniMax M2.1 executes steps sequentially without reordering or omission. M2 occasionally dropped or shuffled later steps in long chains.
What is the migration path from M2?
Swap the model identifier to
minimax/minimax-m2.1in your API calls. The request and response formats are unchanged.Is MiniMax M2.1 appropriate for a CI bot that reviews every pull request?
Yes, it's a fit. Automated review is asynchronous, so the baseline inference rate carries no penalty. MiniMax M2.1's improved instruction adherence means review criteria apply consistently across every PR.
When should I look past the 2.1 generation entirely?
When your workflow benefits from the plan-then-code architecture that M2.5 introduced, or the multi-agent coordination in M2.7. Those later generations address different design patterns.