Text model
deepseek/deepseek-ocr-2 pricing
Novita AI charges $0.03 per million input tokens and $0.03 per million output tokens for deepseek/deepseek-ocr-2. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.03/ 1M
- Output
- $0.03/ 1M
- Context
- 8.2Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.03 | $0.03 | — | — |
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 | $0.000057 | 100,000 | $5.70 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.000195 | 100,000 | $19.50 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.000384 | 250,000 | $96.00 |
| 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/deepseek-ocr-2, 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 |
|---|---|---|
| novita/meta-llama/llama-3.2-1b-instruct | $0.000038 | 33% |
| novita/paddlepaddle/paddleocr-vl | $0.000038 | 33% |
| deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.000046 | 19% |
| deepinfra/mistralai/Mistral-Nemo-Instruct-2407 | $0.0000405 | 29% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Novita AI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.