DeepSeek-R1: pricing, context window and benchmarks
DeepSeek-R1 is a multimodal model from DeepSeek. It offers a 128,000-token context window, costs $5.83 per million input tokens and $25.23 per million output tokens, and averages 82.8 across the index's benchmark suite.
Pricing
DeepSeek-R1 costs $5.83 per million input tokens and $25.23 per million output tokens. A blended 3:1 input-to-output mix works out to about $10.68 per million tokens. Cached input is listed at $0.83 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.83 | per 1M tokens |
| Output | $25.23 | per 1M tokens |
| Cached input | $0.83 | per 1M tokens |
| Blended 3:1 | $10.68 | estimate per 1M tokens |
| 1M in + 1M out | $31.06 | 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 | 83.8 | 85 | 86th | |
| GPQA Diamond | 77.8 | 89 | 85th | |
| SWE-bench Verified | 72.2 | 73 | 88th | |
| HumanEval | 86.4 | 97 | 84th | |
| MATH-500 | 89.1 | 55 | 91th | |
| AIME 2025 | 81.1 | 72 | 88th | |
| LiveCodeBench | 77.4 | 70 | 88th | |
| IFEval | 91.0 | 53 | 91th | |
| TruthfulQA | 82.9 | 107 | 82th | |
| HellaSwag | 89.8 | 90 | 85th | |
| MMMU | 79.5 | 66 | 89th | |
| Arena Elo | 1454.1 | 65 | 89th |
What DeepSeek-R1 is good for
DeepSeek-R1 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 $5.83 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- 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 |
|---|---|---|---|---|
| DeepSeek-R1 Instruct | DeepSeek | 1000000 | $5.90 | 83.1 |
| Kimi K2 | Moonshot AI | 128000 | $5.85 | 83.0 |
| GPT-4.1 Turbo | OpenAI | 1000000 | $16.12 | 82.9 |
| Grok 3 Reasoning | xAI | 200000 | $16.07 | 82.9 |
| DeepSeek-R1 | DeepSeek | 128000 | $5.83 | 82.8 |
| Grok 3 | xAI | 128000 | $15.84 | 82.8 |
FAQ
How much does DeepSeek-R1 cost?
DeepSeek-R1 is listed at $5.83 per million input tokens and $25.23 per million output tokens. Cached input is $0.83 per million tokens. A blended 3:1 input-to-output mix is about $10.68 per million tokens.
What is the context window of DeepSeek-R1?
DeepSeek-R1 has a context window of 128,000 tokens and can emit up to 4,096 output tokens per request in this index.
Is DeepSeek-R1 open weights?
Yes. DeepSeek-R1 is listed as an open-weight model under a open weights licence.
How does DeepSeek-R1 score on benchmarks?
DeepSeek-R1 averages 82.8 across the scored benchmarks in this index, ranking #77 of 600 models. Its strongest relative result is Arena Elo at 1454.1.
What is DeepSeek-R1 best for?
DeepSeek-R1 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 $5.83 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.