DeepSeek-V3-0324 API Pricing
DeepSeek-V3-0324 on DeepInfra costs $0.24 per 1M input tokens and $0.90 per 1M output tokens (as of ).
| Input | $0.24 / 1M tokens |
|---|---|
| Output | $0.90 / 1M tokens |
| Cached input (read) | $0.14 |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 164K tokens |
| Max output | 164K tokens |
| Supports | tool calling, prompt caching |
| Deprecation date | None listed |
| API model id | deepseek-ai/DeepSeek-V3-0324 |
| 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) | $0.93 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $1.29 |
| 1 million classification calls (300 in, 5 out each) | $76.50 |
Try your own numbers in the LLM API cost calculator.
Price history
- Between and : cached input price changed from — to $0.14 per 1M tokens.
- Between and : output price changed from $0.88 to $0.90 per 1M tokens.
- Between and : input price changed from $0.25 to $0.24 per 1M tokens.
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| MythoMax-L2-13b | DeepInfra | $0.40 | $0.40 | — | 4K |
| Meta-Llama-3.1-70B-Instruct | DeepInfra | $0.40 | $0.40 | — | 131K |
| Meta-Llama-3.1-70B-Instruct-Turbo | DeepInfra | $0.40 | $0.40 | — | 131K |
| Mixtral-8x7B-Instruct-v0.1 | DeepInfra | $0.40 | $0.40 | — | 33K |
| gemma-4-31B-it-Ultra | DeepInfra | $0.27 | $0.76 | — | 131K |
| gpt-oss-120b-Ultra | DeepInfra | $0.20 | $0.95 | — | 131K |
| DeepSeek-V3.1 | DeepInfra | $0.25 | $0.95 | $0.22 | 164K |
| MiniMax-M2.7 | DeepInfra | $0.25 | $1.00 | $0.05 | 197K |