Model
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Compare providers (sorted by listed input price)
52 of 64 providers publish a price for DeepSeek V4 Flash. The cheapest full-context option is Merge Gateway at $0.035/$0.07 per M — 83% below DeepSeek's own price. Listed prices span 15.1× for identical weights.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.035▼ 44.0%
- Best output /M
- $0.07▼ 44.0%
- Provider coverage
- 83
- 77 at the start · 24 snapshots
Price badge
https://www.vaanalytics.in/badge/deepseek/deepseek-v4-flash.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 →- repricedvia openrouter · Sep 14, 2026
- input: $0.049 → $0.09
- output: $0.098 → $0.18
- cache_read: $0.0098 → $0.018
- new modelvia llmgateway-providers · Sep 13, 2026
- contextvia llmgateway-providers · Sep 13, 2026
- context: 1M → 1.05M tokens
- repricedvia above · Sep 13, 2026
- description: Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding → DeepSeek V4.1 Flash model for reasoning and agentic coding
- attachment: false → true
- release_date: 2026-07-31 → 2026-09-10
- last_updated: 2026-07-31 → 2026-09-10
- +5 more
- new modelvia agentrouter · Sep 13, 2026
- repricedvia openrouter · Sep 13, 2026
- input: $0.089 → $0.049
- output: $0.177 → $0.098
- cache_read: $0.018 → $0.0098
Benchmarks
- SWE-Bench Verified ↗(resolved)report ↗Unclassified source79
Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.
Weights
Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.
licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary
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.