DeepSeek-Coder Chat: pricing, context window and benchmarks
DeepSeek-Coder Chat is a coding model from DeepSeek. It offers a 200,000-token context window, costs $4.20 per million input tokens and $19.27 per million output tokens, and averages 77.3 across the index's benchmark suite.
Pricing
DeepSeek-Coder Chat costs $4.20 per million input tokens and $19.27 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.97 per million tokens. Cached input is listed at $0.54 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.20 | per 1M tokens |
| Output | $19.27 | per 1M tokens |
| Cached input | $0.54 | per 1M tokens |
| Blended 3:1 | $7.97 | estimate per 1M tokens |
| 1M in + 1M out | $23.47 | 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 | 77.9 | 244 | 59th | |
| GPQA Diamond | 74.0 | 168 | 72th | |
| SWE-bench Verified | 64.5 | 221 | 63th | |
| HumanEval | 82.5 | 173 | 71th | |
| MATH-500 | 81.6 | 174 | 71th | |
| AIME 2025 | 70.1 | 255 | 58th | |
| LiveCodeBench | 69.6 | 199 | 67th | |
| IFEval | 85.8 | 163 | 73th | |
| TruthfulQA | 79.9 | 180 | 70th | |
| HellaSwag | 88.1 | 137 | 77th | |
| MMMU | 76.5 | 124 | 79th | |
| Arena Elo | 1414.5 | 170 | 72th |
What DeepSeek-Coder Chat is good for
DeepSeek-Coder Chat 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 $4.20 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-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.
- 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 |
|---|---|---|---|---|
| Hunyuan-Turbo Turbo | Tencent | 65536 | $11.60 | 77.4 |
| Kimi K1.5 Base | Moonshot AI | 65536 | $4.34 | 77.4 |
| Qwen3 Base | Alibaba Cloud | 65536 | $4.33 | 77.4 |
| Reka Core | Reka AI | 32768 | $12.17 | 77.4 |
| DeepSeek-Coder Chat | DeepSeek | 200000 | $4.20 | 77.3 |
| Yi-Lightning | 01.AI | 32768 | $4.22 | 77.2 |
FAQ
How much does DeepSeek-Coder Chat cost?
DeepSeek-Coder Chat is listed at $4.20 per million input tokens and $19.27 per million output tokens. Cached input is $0.54 per million tokens. A blended 3:1 input-to-output mix is about $7.97 per million tokens.
What is the context window of DeepSeek-Coder Chat?
DeepSeek-Coder Chat has a context window of 200,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is DeepSeek-Coder Chat open weights?
Yes. DeepSeek-Coder Chat is listed as an open-weight model under a open weights licence.
How does DeepSeek-Coder Chat score on benchmarks?
DeepSeek-Coder Chat averages 77.3 across the scored benchmarks in this index, ranking #191 of 600 models. Its strongest relative result is Arena Elo at 1414.5.
What is DeepSeek-Coder Chat best for?
DeepSeek-Coder Chat 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 $4.20 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.