Text model
deepseek-ai/deepseek-r1 pricing
Replicate charges $3.75 per million input tokens and $10.00 per million output tokens for deepseek-ai/deepseek-r1. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $3.75/ 1M
- Output
- $10.00/ 1M
- Context
- 65.5Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $3.75 | $10.00 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00962 | 100,000 | $962.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.03 | 100,000 | $2,750.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.05 | 250,000 | $13,250.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with deepseek-ai/deepseek-r1, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| replicate/deepseek-ai/deepseek-v3 | $0.00276 | 71% |
| replicate/deepseek-ai/deepseek-v3.1 | $0.00181 | 81% |
| deepinfra/google/gemini-3.1-pro | $0.0078 | 19% |
| google/deep-research-max-preview-04-2026 | $0.0078 | 19% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Replicate pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.