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.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
DeepSeek$0.66$1.98$0.0221.05M384K99.88%
StreamLakefp8$0.691$1.382$0.0581.02M384K96.04%
Baidufp8$0.693$1.386$0.0571.05M393K94.72%
GMICloudfp8$0.696$1.392$0.0581.05M95.24%
DigitalOcean$0.87$1.74$0.1741.05M95.34%
Ionstreamfp4$1.131$2.262$0.0941.05M393K96.63%
CoreWeavefp8$1.15$2.55$0.201.05M1.05M97.19%
DeepInfrafp8$1.30$2.60$0.101.05M16K99.48%
Alibabafp8$1.416$2.832$0.1181M393K97.04%
Novitafp8$1.44$2.88$0.1211.05M393K99.49%
SiliconFlowfp8$1.502$3.135$0.1351.05M393K94.96%
Venice$1.65$3.301$0.331M33K88.34%
AtlasCloudfp4$1.68$3.38$0.131.05M393K91.34%
BaseTenfp4$1.74$3.48$0.145262K262K98.84%
Parasailfp8$1.74$3.48$0.101.05M1.05M93.10%
Together$1.74$3.48$0.20512K90.65%
Fireworks$1.74$3.48$0.1451.05M
Azure$1.91$3.83$0.161.05M384K95.47%

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.