DeepSeek-V4-Flash is DeepSeek's model priced at $0.14 per 1M input tokens and $0.28 per 1M output tokens, with a context window of about 128K tokens. Below are its full specs and how it stacks up against models from other providers on price and context.
DeepSeek-V4-Flash pricing
| Token type | Price (per 1,000,000 tokens) |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
| Cached input | $0.0028 |
Standard cache-miss input pricing; off-peak discounts may apply.
Source: official DeepSeek pricing.
DeepSeek-V4-Flash specifications
| Spec | Value |
|---|---|
| Vendor | DeepSeek |
| Context window | 128K tokens |
| Input price | $0.14 / 1M tokens |
| Output price | $0.28 / 1M tokens |
| Cached input price | $0.0028 / 1M tokens |
Compare DeepSeek-V4-Flash with other models
Head-to-head pricing and spec comparisons against models from other providers:
- DeepSeek-V4-Flash vs GPT-5.5
- DeepSeek-V4-Flash vs Claude Opus 4.8
- DeepSeek-V4-Flash vs Gemini 3.5 Flash
Running DeepSeek-V4-Flash in production? See its DeepSeek rate limits and common error codes, or estimate spend with the token cost calculator.
Prices change often — these are as of June 2026. Context windows are approximate (some models offer larger beta/long-context tiers) — verify against provider docs. GPT counts are exact via the o200k tokenizer; Anthropic/Google/DeepSeek counts are estimates.