DeepSeek
DeepSeek V4 Flash
DeepSeek V4 Flash by DeepSeek — compare inference API pricing across providers.
Context 1.0M
Input from
$0.090 / 1M tokens
across 4 providers
API Pricing
Cheapest on OpenRouter — 22% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.090 | $0.180 | $0.020 | |
| $0.100 | $0.200 | $0.020 | |
| $0.132 | $0.263 | $0.066 | |
| $0.140 | $0.280 | - |
Prices updated daily. Last check: Jun 27, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
28.7 / 100
Output Speed
115 t/s
Latency (TTFT)
1.1s
Reasoning & Knowledge
- GPQA Diamond71.6%
- Humanity's Last Exam7.0%
Coding
- SciCode37.3%
Agentic & Tool Use
- Terminal-Bench Hard34.1%
- τ²-bench94.4%
Instruction & Long Context
- IFBench47.2%
- Long-Context Reasoning33.3%
Benchmarks measured Jun 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- DeepSeek
- Family
- DeepSeek V4
- Context Window
- 1.0M
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No
- Aliases
- deepseek-ai/DeepSeek-V4-Flash, DeepSeek-V4-Flash, deepseek-v4-flash