Models / DeepSeek / DeepSeek-V3.1
DeepSeek · deepseek
DeepSeek-V3.1
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
$0.50 in · $1.50 out
per 1M tokens · provider rate closest to the median. No first-party DeepSeek price was listed. The reference price is Merge Gateway's rate, the provider closest to the median.
Provider input prices run from $0.19 to $3.00 per 1M tokens. Output prices run from $0.71 to $4.50.
- Context
- 131,072
- Max output
- 8,192
- Cache read
- —
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- No
- Open weights
- Yes
- License
- MIT License
- Released
- Aug 21, 2025
- Updated in source
- Aug 21, 2025
- Knowledge
- —
- Providers
- 9
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| TokenGo | $0.19 | $0.71 | $0.06 | — | — |
| Deep Infra | $0.25 | $0.95 | $0.13 | — | — |
| Vercel AI Gateway | $0.25 | $0.95 | $0.13 | — | — |
| Hugging Face | $0.27 | $1.00 | — | — | — |
| Merge Gatewayreference | $0.50 | $1.50 | — | — | — |
| CoreWeave | $0.55 | $1.65 | $0.55 | — | — |
| Pioneer | $0.56 | $1.68 | $0.56 | $0.56 | — |
| Amazon Bedrock | $0.58 | $1.68 | — | — | — |
| SambaNova | $3.00 | $4.50 | — | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Cheapest summarization — clears the bar