DeepSeek-V3.2 Chat: pricing, context window and benchmarks
DeepSeek-V3.2 Chat is a multimodal model from DeepSeek. It offers a 1,000,000-token context window, costs $5.80 per million input tokens and $26.43 per million output tokens, and averages 82.5 across the index's benchmark suite.
Pricing
DeepSeek-V3.2 Chat costs $5.80 per million input tokens and $26.43 per million output tokens. A blended 3:1 input-to-output mix works out to about $10.96 per million tokens. Cached input is listed at $0.49 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.80 | per 1M tokens |
| Output | $26.43 | per 1M tokens |
| Cached input | $0.49 | per 1M tokens |
| Blended 3:1 | $10.96 | estimate per 1M tokens |
| 1M in + 1M out | $32.23 | 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 | 82.5 | 114 | 81th | |
| GPQA Diamond | 78.0 | 85 | 86th | |
| SWE-bench Verified | 69.6 | 120 | 80th | |
| HumanEval | 87.9 | 74 | 88th | |
| MATH-500 | 90.2 | 46 | 92th | |
| AIME 2025 | 81.0 | 75 | 88th | |
| LiveCodeBench | 77.9 | 65 | 89th | |
| IFEval | 88.6 | 91 | 85th | |
| TruthfulQA | 86.3 | 45 | 93th | |
| HellaSwag | 89.2 | 107 | 82th | |
| MMMU | 76.0 | 140 | 77th | |
| Arena Elo | 1462.2 | 48 | 92th |
What DeepSeek-V3.2 Chat is good for
DeepSeek-V3.2 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 $5.80 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.
Strengths
- 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.
- 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 |
|---|---|---|---|---|
| Grok 3 | xAI | 128000 | $15.84 | 82.8 |
| DeepSeek-V3.2 Chat | DeepSeek | 1000000 | $5.80 | 82.5 |
| DeepSeek-R1 Chat | DeepSeek | 400000 | $5.62 | 82.4 |
| GPT-4.1 | OpenAI | 1000000 | $15.71 | 82.4 |
| Claude 3.7 Sonnet Turbo | Anthropic | 200000 | $15.56 | 82.3 |
| Kimi K2 Instruct | Moonshot AI | 1000000 | $5.80 | 82.3 |
FAQ
How much does DeepSeek-V3.2 Chat cost?
DeepSeek-V3.2 Chat is listed at $5.80 per million input tokens and $26.43 per million output tokens. Cached input is $0.49 per million tokens. A blended 3:1 input-to-output mix is about $10.96 per million tokens.
What is the context window of DeepSeek-V3.2 Chat?
DeepSeek-V3.2 Chat 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-V3.2 Chat open weights?
Yes. DeepSeek-V3.2 Chat is listed as an open-weight model under a open weights licence.
How does DeepSeek-V3.2 Chat score on benchmarks?
DeepSeek-V3.2 Chat averages 82.5 across the scored benchmarks in this index, ranking #79 of 600 models. Its strongest relative result is Arena Elo at 1462.2.
What is DeepSeek-V3.2 Chat best for?
DeepSeek-V3.2 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 $5.80 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.