MiniMax M2.1
MiniMax M2.1 is MiniMax's language model with a 1.0M context window and up to 197K output tokens, available from 8 providers, starting at $0.290 / 1M input and $0.950 / 1M output. A refined M2.1 sub-version of MiniMax's MoE language model with improved reasoning, tool-use, and implicit caching for agentic tasks.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | Flex | Priority | |||||
|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.290 | $0.950 | $0.030 | — | — | — | — | — | — |
 Amazon Bedrock | $0.300 | $1.20 | N/A | $0.150 | $0.600 | $0.150 | $0.600 | $0.525 | $2.10 |
 Fireworks AI | $0.300 | $1.20 | $0.030 | — | — | — | — | — | — |
 GMI Cloud | $0.300 | $1.20 | N/A | — | — | — | — | — | — |
 Hugging Face | $0.300 | $1.20 | N/A | — | — | — | — | — | — |
MiniMax | $0.300 | $1.20 | $0.030 | — | — | — | — | — | — |
 Novita | $0.300 | $1.20 | $0.030 | — | — | — | — | — | — |
 Vercel AI Gateway | $0.300 | $1.20 | $0.030 | — | — | — | — | — | — |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiniMax M2.7 | 205K | $0.279 | $1.20 | Available | |
| MiniMax M2.5 | 1.0M | $0.150 | $1.15 | Available | |
| MiniMax M2.1 | 1.0M | $0.290 | $0.950 | Current |