DeepSeek · open weights
DeepSeek V4 Pro 0813 API pricing by provider
DeepSeek V4 Pro 0813 is available from 22 providers. The cheapest is Baidu at $0.132 input / $0.396 output per 1M tokens (FP8). DeepSeek’s own API charges $0.66 / $1.98, 80% more than the cheapest host. The priciest host, Venice, charges 12.5x the cheapest.
Prices from the OpenRouter API, retrieved October 26, 2026. Weights: deepseek-ai/DeepSeek-V4-Pro-0813.
| Provider | Precision | Input / 1M | Output / 1M | Document Q&A / month | Context | Max output |
|---|---|---|---|---|---|---|
| Baidu | fp8 | $0.132 | $0.396 | $64.68 | 1.05M | 393K |
| Sail Research | fp4 | $0.45 | $0.80 | $204.00 | 1.05M | 384K |
| Alibaba | — | $0.5808 | $1.742 | $284.59 | 1M | 393K |
| Alibaba | — | $0.66 | $1.98 | $323.40 | 1M | 393K |
| StreamLake | — | $0.66 | $1.98 | $323.40 | 1.02M | 384K |
| DeepSeekcreator | — | $0.66 | $1.98 | $323.40 | 1.05M | 393K |
| Ionstream | — | $0.37 | $2.93 | $235.90 | 1.05M | 944K |
| Wafer | mxfp4 | $0.285 | $4.30 | $243.00 | 1.05M | 944K |
| Phala | — | $0.957 | $2.878 | $469.13 | 1.05M | 393K |
| Novita | fp8 | $0.99 | $2.97 | $485.10 | 1.05M | 393K |
| GMICloud | fp8 | $1.056 | $3.168 | $517.44 | 1.05M | 944K |
| DeepInfra | fp8 | $1.30 | $2.60 | $598.00 | 1.05M | 16K |
| DekaLLM | — | $1.08 | $3.80 | $546.00 | 1.05M | 944K |
| CoreWeave | fp8 | $1.31 | $3.96 | $642.80 | 1.05M | 944K |
| BaseTen | fp4 | $1.32 | $3.96 | $646.80 | 1.05M | 262K |
| AtlasCloud | fp8 | $1.32 | $3.96 | $646.80 | 1.05M | 393K |
| Parasail | fp8 | $1.32 | $3.96 | $646.80 | 1.05M | 944K |
| Together | — | $1.32 | $3.96 | $646.80 | 1.05M | 944K |
| DigitalOcean | — | $1.32 | $3.96 | $646.80 | 1.05M | 944K |
| SiliconFlow | fp8 | $1.32 | $3.96 | $646.80 | 1.05M | 393K |
| Cloudflare | — | $1.32 | $3.96 | $646.80 | 1.05M | 944K |
| Relace | fp4 | $0.1188 | $8.00 | $287.52 | 1.05M | 393K |
| Venice | — | $1.65 | $4.95 | $808.50 | 1M | 33K |
Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.
Compare with DeepSeek’s API page
See benchmarks, cached-input pricing and comparisons for DeepSeek V4 Pro on its model page.
Frequently asked questions
- What is the cheapest DeepSeek V4 Pro 0813 API provider?
- Baidu is the cheapest healthy provider we track at $0.132 per 1M input tokens and $0.396 per 1M output tokens.
- How much does DeepSeek V4 Pro 0813 cost?
- Across 22 providers, input prices range from $0.1188 to $1.65 per 1M tokens and output prices from $0.396 to $8.00.
- What is DeepSeek V4 Pro 0813’s context window?
- DeepSeek V4 Pro 0813 supports up to 1.05M tokens, but some providers serve a smaller context window — check the table before choosing.
Other open-weight models
- DeepSeek V4.1 Flashfrom $0.09 / $0.25
- Kimi K3from $0.17 / $7.697
- GLM 5.3from $0.0699 / $1.40
- GLM 5.3 Flashfrom $0.0413 / $0.0758
- Qwen3.8 27Bfrom $0.02 / $0.50
- MiniMax M3from $0.224 / $0.88
- gpt-oss-120bfrom $0.03 / $0.15
- gpt-oss-20bfrom $0.018 / $0.09
- Llama 4 Maverickfrom $0.1875 / $0.6525
- Llama 3.3 70B Instructfrom $0.10 / $0.32
- Gemma 4 31Bfrom $0.10 / $0.34
- Mistral Small 4from $0.15 / $0.60
- Nemotron 3 Superfrom $0.085 / $0.40