DeepSeek-R1 Instruct: pricing, context window and benchmarks
DeepSeek-R1 Instruct is a frontier model from DeepSeek. It offers a 1,000,000-token context window, costs $5.90 per million input tokens and $26.49 per million output tokens, and averages 83.1 across the index's benchmark suite.
Pricing
DeepSeek-R1 Instruct costs $5.90 per million input tokens and $26.49 per million output tokens. A blended 3:1 input-to-output mix works out to about $11.05 per million tokens. Cached input is listed at $0.54 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.90 | per 1M tokens |
| Output | $26.49 | per 1M tokens |
| Cached input | $0.54 | per 1M tokens |
| Blended 3:1 | $11.05 | estimate per 1M tokens |
| 1M in + 1M out | $32.39 | 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 | 84.9 | 63 | 90th | |
| GPQA Diamond | 81.4 | 37 | 94th | |
| SWE-bench Verified | 72.4 | 69 | 89th | |
| HumanEval | 88.0 | 72 | 88th | |
| MATH-500 | 86.2 | 88 | 85th | |
| AIME 2025 | 77.6 | 120 | 80th | |
| LiveCodeBench | 79.6 | 49 | 92th | |
| IFEval | 88.9 | 83 | 86th | |
| TruthfulQA | 82.2 | 127 | 79th | |
| HellaSwag | 91.1 | 59 | 90th | |
| MMMU | 81.5 | 37 | 94th | |
| Arena Elo | 1447.7 | 80 | 87th |
What DeepSeek-R1 Instruct is good for
DeepSeek-R1 Instruct sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $5.90 per million input tokens and a 1,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.
Strengths
- Top-tier average benchmark score (83.1), placing it #72 of 600.
- Large 1,000,000-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.
Trade-offs
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude 3.7 Sonnet Pro | Anthropic | 128000 | $16.07 | 83.3 |
| DeepSeek-R1 Instruct | DeepSeek | 1000000 | $5.90 | 83.1 |
| Grok 3 Turbo | xAI | 128000 | $15.97 | 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 |
FAQ
How much does DeepSeek-R1 Instruct cost?
DeepSeek-R1 Instruct is listed at $5.90 per million input tokens and $26.49 per million output tokens. Cached input is $0.54 per million tokens. A blended 3:1 input-to-output mix is about $11.05 per million tokens.
What is the context window of DeepSeek-R1 Instruct?
DeepSeek-R1 Instruct has a context window of 1,000,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is DeepSeek-R1 Instruct open weights?
Yes. DeepSeek-R1 Instruct is listed as an open-weight model under a open weights licence.
How does DeepSeek-R1 Instruct score on benchmarks?
DeepSeek-R1 Instruct averages 83.1 across the scored benchmarks in this index, ranking #72 of 600 models. Its strongest relative result is Arena Elo at 1447.7.
What is DeepSeek-R1 Instruct best for?
DeepSeek-R1 Instruct sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $5.90 per million input tokens and a 1,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.