DeepSeek V4 Flash
High-volume coding and text workloads where budget is the top priority.
What are DeepSeek V4 Flash's specs and price?
DeepSeek V4 Flash, built by DeepSeek, ships a 128K-token context window and a 32K-token max output, released 2026-05. It supports text input and costs $0.17 per million blended tokens, the 5th-cheapest of 32 models we track.
Specs
| Context window | 128K tokens |
| Max output | 32K tokens |
| Modalities | text |
| Extended thinking | No |
| Released | 2026-05 |
| Knowledge cutoff | 2026-02 |
| Provider | DeepSeek |
Verified 2026-08-08 — source.
Where it ranks
Strengths
- Latest DeepSeek flagship, non-thinking mode
- Aggressively cheap per-token pricing
- Strong algorithmic coding
More about DeepSeek V4 Flash
FAQ
What is DeepSeek V4 Flash's context window?
DeepSeek V4 Flash has a 128K-token context window and a 32K-token max output — the 30th-largest context of the 32 current models we track. Source: https://api-docs.deepseek.com/quick_start/pricing, verified 2026-08-08.
Does DeepSeek V4 Flash support vision or audio input?
No — DeepSeek V4 Flash is text-only as of 2026-08-08.
Does DeepSeek V4 Flash have a reasoning or extended-thinking mode?
No — DeepSeek V4 Flash does not expose a separate reasoning/extended-thinking mode.
When was DeepSeek V4 Flash released, and what is its knowledge cutoff?
DeepSeek V4 Flash was released 2026-05 with a knowledge cutoff of 2026-02.
How much does DeepSeek V4 Flash cost, and who provides it?
DeepSeek V4 Flash is served by DeepSeek at $0.17/M blended tokens (3:1 input:output) — the 5th-cheapest of 32 current models. Full pricing breakdown: /llm-api-pricing/deepseek-v4-flash.