DeepSeek R1 Turbo
DeepSeek R1 Turbo is DeepSeek's language model with a 64K context window and up to 16K output tokens, available from 3 providers, starting at $0.7 / 1M input and $2.50 / 1M output. A turbo-speed variant of DeepSeek R1 optimized for faster inference while preserving the model's strong mathematical and logical reasoning abilities.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $1.00 | $3.00 | |
| $0.7 | $2.50 | |
| $0.7 | $2.50 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek R1 Turbo | — | 64K | $0.700 | $2.50 | Current |
| DeepSeek R1 528 Turbo | — | 33K | $1.00 | $3.00 | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek R1T2 Chimera | — | 164K | — | — | |
| DeepSeek R1 528 | — | 164K | $0.200 | $0.250 | |
| DeepSeek R1 Distill Qwen 32B | — | 131K | $0.150 | $0.150 | |
| DeepSeek R1 Distill Llama 70B | — | 131K | $0.200 | $0.375 | |
| DeepSeek R1 | — | 164K | $0.280 | $0.400 | |
| DeepSeek R1 Distill Qwen 14B | — | — | 131K | $0.070 | $0.070 |
| DeepSeek R1 Distill Llama 8B | — | — | 131K | $0.025 | $0.025 |
| DeepSeek R1 Distill Qwen 1.5B | — | — | 131K | $0.090 | $0.090 |
| DeepSeek R1 528B | — | — | 131K | $0.550 | $2.19 |
| DeepSeek R1 671B | — | — | 131K | $0.800 | $0.800 |