Model
DeepSeek V4 Flash 0731
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
8 providersreleased Jul 31, 2026knowledge cutoff 2025-05open weights
$0.08
best input /M · OpenRouter
$0.18
best output /M
1M
context window
384K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| OpenRouter deepseek/deepseek-v4-flash-0731 | $0.08 | $0.18 | $0.016 | — | 1.31M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| Ambient deepseek/deepseek-v4-flash-0731 | $0.08 | $0.18 | $0.016 | $0 | 1.05M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| Perplexity Agent deepseek/deepseek-v4-flash-0731 | $0.13 | $0.26 | $0.028 | — | 1M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| Vercel AI Gateway deepseek/deepseek-v4-flash-0731 | $0.13 | $0.26 | $0.028 | — | 1M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| NanoGPT deepseek/deepseek-v4-flash-0731 | $0.14 | $0.28 | $0.014 | — | 1M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| Kilo Gateway deepseek/deepseek-v4-flash-0731 | $0.14 | $0.28 | $0.028 | — | 1.05M | reasoningtoolsstructuredno vision | Jul 31, 2026 | |
| Merge Gateway deepseek/deepseek-v4-flash-0731 | $0.22 | $0.66 | $0.0070 | — | 1M | reasoningtoolsno structuredno vision | Jul 31, 2026 | |
| TensorX deepseek/deepseek-v4-flash-0731 | $0.25 | $0.3 | $0.06 | — | 1.05M | reasoningtoolsstructuredno vision | Jul 31, 2026 |
Price badge
https://models.sutraworks.ai/badge/deepseek/deepseek-v4-flash-0731.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- contextvia kilo · Aug 21, 2026
- limit.output: $393216 → $384000
- repricedvia openrouter · Aug 21, 2026
- limit.output: $393216 → $384000
- input: $0.14 → $0.08
- output: $0.28 → $0.18
- cache_read: $0.028 → $0.016
Benchmarks
Weights
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.