DeepSeek R1 671B
DeepSeek R1 671B is DeepSeek's language model with a 131K context window, starting at $0.8 / 1M input and $0.8 / 1M output. The full-scale 671B-parameter DeepSeek R1 reasoning model using a Mixture-of-Experts architecture for advanced mathematical and logical reasoning.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.8 | $0.8 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host DeepSeek R1 671B, ranked by cheapest on-demand price. The model needs about 1610 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region |
|---|---|---|---|---|---|
| p6-b300.48xlarge |  AWS | 8× B300 | 2149 GB | $142.42/hr |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek R1T2 Chimera | 164K | — | — | Available | |
| DeepSeek R1 528 | 164K | $0.200 | $0.250 | Deprecated | |
| DeepSeek R1 Distill Qwen 32B | 131K | $0.150 | $0.150 | Available | |
| DeepSeek R1 Distill Llama 70B | 131K | $0.200 | $0.375 | Deprecated | |
| DeepSeek R1 | 164K | $0.280 | $0.400 | Deprecated | |
| DeepSeek R1 671B | — | 131K | $0.800 | $0.800 | Current |
| DeepSeek R1 Distill Qwen 14B | — | 131K | $0.070 | $0.070 | Deprecated |
| DeepSeek R1 Distill Llama 8B | — | 131K | $0.025 | $0.025 | Available |
| DeepSeek R1 Distill Qwen 1.5B | — | 131K | $0.090 | $0.090 | Deprecated |
| DeepSeek R1 528 Turbo | — | 33K | $1.00 | $3.00 | Available |
| DeepSeek R1 528B | — | 128K | — | — | Deprecated |