All models
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Modalities
Text
In / Out price
$1.168 / $2.336 per 1M
Context
1.05M · 393K out
Released
Aug 12, 2026
Providers
Live list prices and uptime across 18 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| DeepSeek | $0.66 | $1.98 | $0.022 | 1.05M | 384K | 99.88% |
| StreamLakefp8 | $0.691 | $1.382 | $0.058 | 1.02M | 384K | 96.04% |
| Baidufp8 | $0.693 | $1.386 | $0.057 | 1.05M | 393K | 94.72% |
| GMICloudfp8 | $0.696 | $1.392 | $0.058 | 1.05M | — | 95.24% |
| DigitalOcean | $0.87 | $1.74 | $0.174 | 1.05M | — | 95.34% |
| Ionstreamfp4 | $1.131 | $2.262 | $0.094 | 1.05M | 393K | 96.63% |
| CoreWeavefp8 | $1.15 | $2.55 | $0.20 | 1.05M | 1.05M | 97.19% |
| DeepInfrafp8 | $1.30 | $2.60 | $0.10 | 1.05M | 16K | 99.48% |
| Alibabafp8 | $1.416 | $2.832 | $0.118 | 1M | 393K | 97.04% |
| Novitafp8 | $1.44 | $2.88 | $0.121 | 1.05M | 393K | 99.49% |
| SiliconFlowfp8 | $1.502 | $3.135 | $0.135 | 1.05M | 393K | 94.96% |
| Venice | $1.65 | $3.301 | $0.33 | 1M | 33K | 88.34% |
| AtlasCloudfp4 | $1.68 | $3.38 | $0.13 | 1.05M | 393K | 91.34% |
| BaseTenfp4 | $1.74 | $3.48 | $0.145 | 262K | 262K | 98.84% |
| Parasailfp8 | $1.74 | $3.48 | $0.10 | 1.05M | 1.05M | 93.10% |
| Together | $1.74 | $3.48 | $0.20 | 512K | — | 90.65% |
| Fireworks | $1.74 | $3.48 | $0.145 | 1.05M | — | — |
| Azure | $1.91 | $3.83 | $0.16 | 1.05M | 384K | 95.47% |
Implicit prompt caching available — repeated context bills at the cache read rate.
Capabilities
Tool calling
Reasoning
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
top_k
top_logprobs
top_p
Pricing detail
- Input
- $1.168
- Output
- $2.336
- Cache read
- $0.099
- Cache write
- —
USD per 1M tokens.