Models · DeepSeek
DeepSeek V4 Flash
DeepSeek V4 Flash offers frontier-level performance at an unprecedented price point. With cache-hit pricing as low as $0.0028 per 1M input tokens, it's one of the most cost-effective high-quality models available.
Input $0.30 per 1M tokens
Output $1.20 per 1M tokens
Context 1M tokens · $1.50 combined per 1M
Benchmark performance
Source: Artificial Analysis. Updated 2026-09-20.
Key strengths
- — Exceptional cost efficiency
- — 1M token context window
- — Strong coding and reasoning
- — Cache-hit pricing dramatically reduces costs
Best use cases
- Cost-sensitive production deployments
- Large-scale document processing
- Coding and development workflows
- Applications with high cache hit rates
Pricing details
| Input (per 1M tokens) | $0.30 |
| Output (per 1M tokens) | $1.20 |
| Context window | 1M tokens |
| Architecture | Proprietary MoE architecture, 1M context, optimized for extreme cost efficiency with context caching |
| Provider | DeepSeek |
Cache hit: $0.0028 input
Recent coverage
Qwen3.8-Omni-Flash Cuts Gemini Pricing by 80% for Multimodal AI
Vantora secures $100M to build proprietary AI startups for corporate giants
Jina AI's new OCR hits 2.57 pages/sec on A100
Qwen3.8-Omni-Flash Cuts Video Tokens by 46% With Agentic Reasoning
TACLS AI cuts flash flood warning lag, aiming to save lives
The sharpest AI news, curated daily.
One email each morning. Summarized, sourced, and skimmable in under three minutes.
Pricing data is sourced from official API documentation and updated weekly. Actual costs may vary based on prompt caching, batch processing, service tiers, and regional pricing. Inblix is not affiliated with DeepSeek.