All models

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Modalities
Text
In / Out price
$0.14 / $0.28 per 1M
Context
1.05M · 393K out
Released
Jul 31, 2026

Providers

Live list prices and uptime across 28 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
Decartfp4$0.06$0.121$0.012262K262K96.97%
StreamLakefp8$0.061$0.123$0.0121.02M384K96.92%
DigitalOcean$0.08$0.252$0.0251.05M96.53%
DeepInfrafp8$0.08$0.18$0.0161.05M384K99.87%
OpenInferencefp4$0.08$0.18$0.028262K262K99.51%
GMICloudfp8$0.084$0.168$0.0171.05M98.08%
Sail Researchfp4$0.09$0.18$0.02262K262K93.98%
Relacefp4$0.105$0.21$0.0211.05M1.05M91.32%
BaseTenfp8$0.13$0.26$0.0281.05M1.05M99.88%
CoreWeavefp8$0.13$0.28$0.07262K262K99.96%
Inceptronfp4$0.13$0.28$0.031.05M1.05M97.87%
Morphbf16$0.139$0.278$0.071.05M1.05M93.45%
Fireworks$0.14$0.28$0.0281.05M95.13%
AkashMLfp8$0.14$0.28$0.02131K131K96.62%
Novitafp8$0.14$0.28$0.0281.05M393K92.01%
Together$0.14$0.28$0.031.05M96.73%
Parasailfp8$0.14$0.28$0.071.05M1.05M98.19%
AtlasCloudfp4$0.14$0.28$0.0281.05M393K98.78%
SiliconFlowfp8$0.14$0.28$0.0281.05M393K98.70%
Ambientfp4$0.14$0.28$0.0281.05M1.05M97.41%
Baidufp8$0.14$0.28$0.0281.05M131K99.48%
Io Netfp8$0.149$0.32$0.077262K66K99.75%
Mancer 2fp8$0.15$0.501.05M1.05M93.90%
Venice$0.175$0.35$0.0351M33K93.91%
Phala$0.20$0.40$0.071.05M393K96.20%
DeepSeekfp8$0.22$0.66$0.0071.05M384K99.84%
Wafer$0.28$0.56$0.071.05M1.05M98.73%
Cloudflare$0.44$1.32$0.0141.05M1.05M99.97%

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
parallel_tool_calls
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
top_a
top_k
top_logprobs
top_p

Pricing detail

Input
$0.14
Output
$0.28
Cache read
$0.028
Cache write

USD per 1M tokens.