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
$0.08 / $0.18 per 1M
Context
1.31M · 384K out
Released
Jul 31, 2026
Providers
Live list prices and uptime across 28 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| OpenInferencefp8 | $0.03 | $0.07 | $0.005 | 1.05M | 944K | 99.80% |
| Baidufp8 | $0.04 | $0.119 | $0.001 | 1.05M | 131K | 99.93% |
| Relacefp4 | $0.04 | $0.08 | $0.008 | 1.05M | 944K | 99.50% |
| Inceptronfp4 | $0.056 | $0.127 | $0.004 | 1.05M | 944K | 99.84% |
| DeepInfrafp8 | $0.06 | $0.18 | $0.015 | 1.05M | 384K | 99.70% |
| StreamLakefp8 | $0.062 | $0.185 | $0.002 | 1.02M | 384K | 99.71% |
| Sail Researchfp4 | $0.078 | $0.36 | $0.024 | 1.05M | 944K | 98.86% |
| DigitalOcean | $0.08 | $0.252 | $0.025 | 1.05M | 944K | 97.66% |
| Makora | $0.09 | $0.195 | $0.02 | 1M | 384K | 99.35% |
| Wafer | $0.10 | $0.25 | $0.05 | 1.05M | 944K | 99.89% |
| Rekafp4 | $0.11 | $0.66 | $0.007 | 262K | 131K | 99.77% |
| Morphbf16 | $0.123 | $0.347 | $0.031 | 1.05M | 944K | 99.99% |
| BaseTenfp8 | $0.13 | $0.26 | $0.028 | 1.05M | 944K | 99.84% |
| BaseTenfp8 | $0.13 | $0.26 | $0.028 | 1.05M | 384K | 99.82% |
| CoreWeavefp8 | $0.13 | $0.28 | $0.07 | 262K | 236K | 99.77% |
| Together | $0.14 | $0.28 | $0.03 | 1.05M | 944K | 99.76% |
| Parasailfp8 | $0.14 | $0.28 | $0.05 | 1.05M | 944K | 99.99% |
| Venice | $0.175 | $0.35 | $0.035 | 1M | 33K | 99.37% |
| Mancer 2fp8 | $0.175 | $0.50 | — | 1.05M | 944K | 99.32% |
| Fireworks | $0.22 | $0.66 | $0.007 | 1.05M | 944K | 97.36% |
| SiliconFlowfp8 | $0.22 | $0.66 | $0.028 | 1.05M | 393K | 99.57% |
| GMICloudfp4 | $0.286 | $0.858 | $0.009 | 1.05M | 944K | 99.73% |
| NextBitfp8 | $0.352 | $1.056 | $0.012 | 1.05M | 944K | 99.91% |
| Alibaba | $0.352 | $1.056 | $0.035 | 1M | 393K | 99.99% |
| Novitafp8 | $0.409 | $1.228 | $0.026 | 1.05M | 393K | 99.99% |
| Phala | $0.44 | $1.32 | $0.028 | 1.05M | 393K | 99.67% |
| AtlasCloudfp4 | $0.44 | $1.32 | $0.028 | 1.05M | 393K | 99.28% |
| Cloudflare | $0.44 | $1.32 | $0.014 | 1.31M | 1.18M | 99.98% |
No implicit prompt caching; cache reads require explicit cache control.
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
- $0.08
- Output
- $0.18
- Cache read
- $0.016
- Cache write
- —
USD per 1M tokens.