DeepSeek V4 Pro 0813 API pricing
As of October 22, 2026, DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens on DeepSeek's own API, with cached input at $0.022 per million.
DeepSeek V4 Pro 0813 benchmarks and specs · Every DeepSeek model's price
- Input, per million tokens$0.66
- Output, per million tokens$1.98
- Cached input, per million$0.022
- Context window1.05M tokens
- Max output393K tokens
- Output speed91 tok/s
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0016 | $1.65 | Yes |
| Repository review | 50K input + 3K output tokens | $0.039 | $38.94 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.152 | $151.80 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.10 | $100.00 |
Price history
We have read DeepSeek's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.66 input, $1.98 output
Cheaper models as good as DeepSeek V4 Pro 0813
Models within two points of DeepSeek V4 Pro 0813 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 60.8 · 86% cheaper output
- Claude Haiku 5.5$0.50 Overall 67.6 against 60.8 · 75% cheaper output
- GLM 5.3 Flash$0.50 Overall 66.0 against 60.8 · 75% cheaper output
- GPT-6 Luna$0.50 Overall 59.7 against 60.8 · 75% cheaper output
- DeepSeek V4.1 Flash 1017$0.60 Overall 67.6 against 60.8 · 70% cheaper output
DeepSeek V4 Pro 0813 pricing questions
- How much does DeepSeek V4 Pro 0813 cost per million tokens?
- $0.66 per million input tokens and $1.98 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does DeepSeek V4 Pro 0813 support prompt caching?
- Yes. OpenRouter lists cached input at $0.022 per million tokens, against $0.66 for uncached input.
- Is there a cheaper model as good as DeepSeek V4 Pro 0813?
- MiMo-V2.6-Flash scores 60.8 on the LLMBenchmark Index, within two points of DeepSeek V4 Pro 0813 or above it, and costs $0.28 per million output tokens.
- Has the price of DeepSeek V4 Pro 0813 changed?
- Not since we started recording it daily on October 21, 2026.