~deepseek/deepseek-pro-latest pricing
Chat~deepseek/deepseek-pro-latest · OpenRouter · context —
Price per 1M tokens
In effect since Oct 16, 2026
| Input (uncached) | $0.2495 |
|---|---|
| OutputIncludes reasoning tokens | $0.7484 |
| Cache read | $0.0079 |
- No long-context tier: one rate for every prompt size.
Price history
3 versions since Oct 15, 2026
- Input
- Output
Show data as table
| Effective from | Input / 1M | Output / 1M |
|---|---|---|
| Oct 15, 2026 | $0.1307 | $8.00 |
| Oct 16, 2026 | $0.225 | $8.00 |
| Oct 16, 2026 | $0.2495 | $0.7484 |
| Oct 16, 2026 | $0.2495 | $0.7484 |
Cost calculator
Calculated with the same function that AI Cost Map uses for your real events.
Includes reasoning tokens.
Read from the prompt cache.
Cost per call
$0.0009
Cost per month
$87.30
Similar models
Same model type, nearest blended price (3 input : 1 output).
| Model | Input | Output | Context | Blended vs this |
|---|---|---|---|---|
| ~deepseek/deepseek-pro-latest (this model) OpenRouter | $0.2495 | $0.7484 | — | — |
| cohere.command-light-text-v14 AWS Bedrock | $0.30 | $0.60 | — | × 1.0 |
| qwen/qwen2.5-vl-72b-instruct Nebius AI Studio | $0.25 | $0.75 | — | × 1.0 |
| qwen/qwen-mt-plus Novita AI | $0.25 | $0.75 | — | × 1.0 |
| cognitivecomputations/dolphin-mistral-24b-venice-edition OpenRouter | $0.20 | $0.90 | — | × 1.0 |
| inception/mercury-2 OpenRouter | $0.25 | $0.75 | — | × 1.0 |
| qwen/qwen3-vl-8b-instruct OpenRouter | $0.25 | $0.75 | — | × 1.0 |