DeepSeek R1 Turbo
DeepSeek R1 Turbo is DeepSeek's language model with a 64K context window and up to 16K output tokens, available from 2 providers, starting at $0.700 / 1M input and $2.50 / 1M output. A high-throughput variant of DeepSeek R1 optimized for faster inference while retaining the model's strong open-source reasoning capabilities.
DeepSeek's language model with a 64K context window and up to 16K output tokens, available from 2 providers, starting at $0.700 / 1M input and $2.50 / 1M output. A high-throughput variant of DeepSeek R1 optimized for faster inference while retaining the model's strong open-source reasoning capabilities.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities3/13
✓
·
✓
✓
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Novita | $0.700 | $2.50 |
 DeepInfra | $1.00 | $3.00 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek R1 Turbo | — | 64K | $0.700 | $2.50 | Current |
| DeepSeek R1 528B Turbo | — | 33K | — | — | Available |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek R1 0528 | — | 164K | $0.200 | $0.600 | |
| DeepSeek R1 528B | — | 164K | — | — | |
| DeepSeek R1 Distill Qwen 32B | — | 131K | $0.270 | $0.270 | |
| DeepSeek R1 Distill Llama 70B | — | 131K | $0.200 | $0.600 | |
| DeepSeek R1 | — | 164K | $0.280 | $0.400 | |
| DeepSeek R1 | — | — | — | — | — |
| DeepSeek R1 0528 Distill Qwen3 8B | — | — | 131K | $0.200 | $0.200 |
| DeepSeek R1 528 Qwen3 8B | — | — | 128K | — | — |
| DeepSeek R1 671B | — | — | 131K | $0.800 | $0.800 |
| DeepSeek R1 Basic | Basic | — | 128K | $0.550 | $2.19 |