DeepSeek V4 Flash 0731 pricing & benchmarks
DeepSeek V4 Flash 0731 is available from DeepSeek at $0.440 per million input tokens and $1.32 per million output tokens ($0.660 blended at 3:1). It accepts up to 1,048,576 tokens of context. 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....
Pricing
Per million tokens · OpenRouter
Input$0.440
Output$1.32
Blended (3:1)$0.660
Specification
deepseek/deepseek-v4-flash-0731
Context window1.0M
Max output131K
ReleasedJul 2026
LicenceOpen weights
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 91.0% ±1.8 | max effort | 2026-08-02 | Independently run · Epoch AI |
| FrontierMath T1–3 | 57.5% ±2.9 | max effort | 2026-08-02 | Independently run · Epoch AI |
| FrontierMath T4 | 24.4% ±6.8 | max effort | 2026-08-02 | Independently run · Epoch AI |
| OTIS Mock AIME | 94.4% ±2.1 | max effort | 2026-08-02 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| GPT-5.6 Luna | OpenAI | $0.450 (−32%) | 91.6% | Compare → |
Where to run DeepSeek V4 Flash 0731
26 options across 23 providers · 8.8× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Relace | $0.075 | $0.048 / $0.157 | 1.0M | fp4 | 100.0% |
| DeepInfra | $0.090 | $0.060 / $0.180 | 1.0M | fp8 | 100.0% |
| DigitalOcean | $0.149 | $0.119 / $0.238 | 1.0M | — | 100.0% |
| Sail Research (us) | $0.150 | $0.150 / $0.150 | 1.0M | fp4 | 100.0% |
| Sail Research | $0.150 | $0.150 / $0.150 | 1.0M | fp4 | 100.0% |
| BaseTen | $0.163 | $0.130 / $0.260 | 1.0M | fp8 | 93.7% |
| BaseTen | $0.163 | $0.130 / $0.260 | 1.0M | fp32 | 93.2% |
| Venice | $0.163 | $0.130 / $0.260 | 1M | — | 97.6% |
| Wafer (fast) | $0.163 | $0.140 / $0.230 | 1.0M | nvfp4 | 100.0% |
| CoreWeave ⚠ 262K context, not 1.0M |
$0.168 | $0.130 / $0.280 | 262K | fp8 | 100.0% |
| Reka ⚠ 262K context, not 1.0M |
$0.169 | $0.050 / $0.528 | 262K | — | 100.0% |
| Cohere | $0.175 | $0.140 / $0.280 | 1.0M | — | 99.7% |
| Together | $0.175 | $0.140 / $0.280 | 1.0M | — | 99.9% |
| Parasail | $0.175 | $0.140 / $0.280 | 1.0M | fp8 | 100.0% |
| Inceptron | $0.186 | $0.110 / $0.413 | 1.0M | fp4 | 99.9% |
| StreamLake | $0.198 | $0.132 / $0.396 | 1.0M | fp8 | 99.9% |
| Mancer 2 | $0.300 | $0.200 / $0.600 | 1.0M | fp8 | 99.8% |
| SiliconFlow | $0.330 | $0.220 / $0.660 | 1.0M | fp8 | 100.0% |
| GMICloud | $0.429 | $0.286 / $0.858 | 1.0M | fp8 | 100.0% |
| Phala | $0.462 | $0.308 / $0.924 | 1.0M | — | 100.0% |
| Alibaba | $0.528 | $0.352 / $1.06 | 1M | — | 99.9% |
| Alibaba (us-east-1) | $0.561 | $0.374 / $1.12 | 1M | — | 100.0% |
| Novita | $0.614 | $0.409 / $1.23 | 1.0M | fp8 | 100.0% |
| Baidu | $0.660 | $0.440 / $1.32 | 1.0M | fp8 | 100.0% |
| AtlasCloud | $0.660 | $0.440 / $1.32 | 1.0M | fp4 | 100.0% |
| Cloudflare | $0.660 | $0.440 / $1.32 | 1.0M | — | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 vs Gemini 3.7 Flash
DeepSeek V4 Flash 0731 vs Grok 4.6
DeepSeek V4 Flash 0731 vs Inkling Small
DeepSeek V4 Flash 0731 vs Qwen3.7 Flash
DeepSeek V4 Flash 0731 vs Claude Opus 5
DeepSeek V4 Flash 0731 vs Gemini 3.6 Flash
DeepSeek V4 Flash 0731 vs Gemini 3.5 Flash Lite
DeepSeek V4 Flash 0731 vs Inkling
FAQ
How much does DeepSeek V4 Flash 0731 cost?
DeepSeek V4 Flash 0731 costs $0.440 per million input tokens and $1.32 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.660 per million tokens.
What is DeepSeek V4 Flash 0731's context window?
DeepSeek V4 Flash 0731 accepts up to 1,048,576 tokens of context, and can generate up to 131,072 output tokens.
How good is DeepSeek V4 Flash 0731 on benchmarks?
DeepSeek V4 Flash 0731 scores 91.0% on GPQA Diamond, independently run and published by Epoch AI. 4 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as DeepSeek V4 Flash 0731?
Yes — 1 model in our catalogue cost less per token than DeepSeek V4 Flash 0731 and score at least as high on the same benchmark. The cheapest is GPT-5.6 Luna at $0.450 per million tokens blended.