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
$0.435 / $0.87 per 1M
Context
1.05M · 384K out
Released
Apr 24, 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 | $0.435 | $0.87 | $0.004 | 1.05M | 384K | 99.89% |
| Baidufp8 | $0.625 | $1.251 | $0.052 | 1.05M | 393K | 96.06% |
| StreamLakefp8 | $0.67 | $1.34 | $0.056 | 1.02M | 384K | 95.49% |
| GMICloudfp8 | $0.679 | $1.357 | $0.057 | 1.05M | — | 92.95% |
| Ionstreamfp4 | $1.131 | $2.262 | $0.094 | 1.05M | 393K | 57.81% |
| Novitafp8 | $1.168 | $2.336 | $0.099 | 1.05M | 393K | 99.13% |
| Waferfp4 | $1.20 | $2.40 | $0.10 | 1.05M | 131K | 91.26% |
| DeepInfrafp4 | $1.30 | $2.60 | $0.10 | 1.05M | 16K | 99.11% |
| DigitalOcean | $1.392 | $2.784 | $0.348 | 262K | — | 91.08% |
| Alibaba | $1.416 | $2.832 | $0.118 | 1M | 393K | 93.06% |
| SiliconFlowfp8 | $1.502 | $3.135 | $0.135 | 1.05M | 393K | 97.71% |
| Venice | $1.65 | $3.301 | $0.33 | 1M | 33K | 85.74% |
| AtlasCloudfp4 | $1.68 | $3.38 | $0.13 | 1.05M | 393K | 98.43% |
| BaseTenfp4 | $1.74 | $3.48 | $0.145 | 262K | 262K | 99.33% |
| Parasailfp8 | $1.74 | $3.48 | $0.10 | 1.05M | 1.05M | 86.60% |
| Together | $1.74 | $3.48 | $0.20 | 512K | — | 94.14% |
| CoreWeavefp8 | $1.74 | $3.48 | $0.14 | 1.05M | 1.05M | 97.42% |
| Fireworks | $1.74 | $3.48 | $0.145 | 1.05M | — | 87.14% |
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
- $0.435
- Output
- $0.87
- Cache read
- $0.004
- Cache write
- —
USD per 1M tokens.