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.
import { streamText } from 'ai'
const result = streamText({ model: 'minimax/minimax-m2.1', prompt: 'Why is the sky blue?'})Playground
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
Ask MiniMax M2.1 anything to try it out.
Providers
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 |
|---|
MiniMax | 205K | 9.9s | 116tps | $0.30/M | $1.20/M | Read:$0.03/M Write:$0.38/M | — | — | +1 | 12/23/2025 | ||
 Novita AI | 205K | 1.4s | 100tps | $0.30/M | $1.20/M | Read:$0.03/M Write:— | — | — | +1 | 12/23/2025 | ||
 Amazon Bedrock | 205K | 0.7s | 147tps | $0.30/M | $1.20/M | Read:$0.15/M Write:— | — | — | +1 | 12/23/2025 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by MiniMax
| Model |
|---|
| 1M | 1.7s | 113tps | $0.60/M$0.30/M | $2.40/M$1.20/M | Read: $0.12/M$0.06/M Write: — | — | — | +2 |  | 05/31/2026 | |||
| 205K | 0.3s | 225tps | $0.15/M | $0.60/M | Read:$0.06/M Write:$0.38/M | — | — | +1 |  +2 | 03/18/2026 | |||
| 205K | 1.0s | 44tps | $0.60/M | $2.40/M | Read:$0.06/M Write:$0.38/M | — | — | +1 | | 03/18/2026 | |||
| 1M | 0.4s | 122tps | $0.07/M | $0.57/M | Read:$0.03/M Write:$0.38/M | — | — | +1 |  +3 | 02/12/2026 | |||
| 205K | 1.1s | 59tps | $0.60/M | $2.40/M | Read:$0.03/M Write:$0.38/M | — | — | +1 | | 02/12/2026 | |||
| 205K | 0.7s | 72tps | $0.30/M | $1.20/M | Read:$0.03/M Write:$0.38/M | — | — | +1 | | 10/27/2025 |
About 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.
What 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: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When 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
Conclusion
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.