MiniMax-Text: pricing, context window and benchmarks
MiniMax-Text is a multimodal model from MiniMax. It offers a 32,768-token context window, costs $4.44 per million input tokens and $18.68 per million output tokens, and averages 77.0 across the index's benchmark suite.
Pricing
MiniMax-Text costs $4.44 per million input tokens and $18.68 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.00 per million tokens. Cached input is listed at $0.45 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.44 | per 1M tokens |
| Output | $18.68 | per 1M tokens |
| Cached input | $0.45 | per 1M tokens |
| Blended 3:1 | $8.00 | estimate per 1M tokens |
| 1M in + 1M out | $23.12 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 78.9 | 213 | 65th | |
| GPQA Diamond | 75.6 | 131 | 78th | |
| SWE-bench Verified | 68.2 | 142 | 76th | |
| HumanEval | 80.5 | 223 | 63th | |
| MATH-500 | 79.0 | 235 | 61th | |
| AIME 2025 | 71.1 | 234 | 61th | |
| LiveCodeBench | 71.4 | 162 | 73th | |
| IFEval | 83.2 | 240 | 60th | |
| TruthfulQA | 78.8 | 225 | 63th | |
| HellaSwag | 85.8 | 224 | 63th | |
| MMMU | 74.0 | 192 | 68th | |
| Arena Elo | 1420.4 | 147 | 76th |
What MiniMax-Text is good for
MiniMax-Text is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.44 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.
Strengths
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Yi-Lightning | 01.AI | 32768 | $4.22 | 77.2 |
| Sonar Pro | Perplexity | 65536 | $11.25 | 77.1 |
| MiniMax-Text | MiniMax | 32768 | $4.44 | 77.0 |
| Llama 3.3 Chat | Meta AI | 32768 | $4.18 | 76.9 |
| Llama 3.1 Turbo | Together AI | 200000 | $4.17 | 76.8 |
| Llama 3.3 Groq | Groq | 32768 | $3.98 | 76.8 |
FAQ
How much does MiniMax-Text cost?
MiniMax-Text is listed at $4.44 per million input tokens and $18.68 per million output tokens. Cached input is $0.45 per million tokens. A blended 3:1 input-to-output mix is about $8.00 per million tokens.
What is the context window of MiniMax-Text?
MiniMax-Text has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is MiniMax-Text open weights?
Yes. MiniMax-Text is listed as an open-weight model under a open weights licence.
How does MiniMax-Text score on benchmarks?
MiniMax-Text averages 77.0 across the scored benchmarks in this index, ranking #194 of 600 models. Its strongest relative result is Arena Elo at 1420.4.
What is MiniMax-Text best for?
MiniMax-Text is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.44 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.