DeepSeek-V3.2 API Pricing
DeepSeek-V3.2 on DeepInfra costs $0.26 per 1M input tokens and $0.38 per 1M output tokens (as of ).
| Input | $0.26 / 1M tokens |
|---|---|
| Output | $0.38 / 1M tokens |
| Cached input (read) | $0.13 |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 164K tokens |
| Max output | — tokens |
| Supports | tool calling, prompt caching |
| Deprecation date | None listed |
| API model id | deepseek-ai/DeepSeek-V3.2 |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $0.71 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $1.34 |
| 1 million classification calls (300 in, 5 out each) | $79.90 |
Try your own numbers in the LLM API cost calculator.
Price history
No price change recorded since .
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| Qwen2.5-VL-32B-Instruct | DeepInfra | $0.20 | $0.60 | — | 128K |
| DeepSeek-R1-Distill-Llama-70B | DeepInfra | $0.20 | $0.60 | — | 131K |
| Llama-3.3-70B-Instruct | DeepInfra | $0.23 | $0.40 | — | 131K |
| Qwen3-235B-A22B | DeepInfra | $0.18 | $0.54 | — | 41K |
| DeepSeek-R1-Distill-Qwen-32B | DeepInfra | $0.27 | $0.27 | — | 131K |
| Qwen3.6-35B-A3B | DeepInfra | $0.10 | $0.95 | — | 262K |
| Qwen3-VL-30B-A3B-Instruct | DeepInfra | $0.15 | $0.60 | — | 262K |
| gpt-oss-120b-Turbo | DeepInfra | $0.15 | $0.60 | — | 131K |