# DeepSeek V4 Flash 0423 API prices

DeepSeek V4 Flash 0423 (deepseek-flash) — 1.0M context, 384k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Venice AI | $0.138 | $0.275 | $0.028 | 1.0M |
| Merge Gateway | $0.139 | $0.278 | — | 131k |
| Ofox | $0.19 | $0.51 | $0.028 | 1.0M |

## Summary

- Cheapest input: $0.138 per 1M tokens (Venice AI)
- Cheapest output: $0.275 per 1M tokens (Venice AI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-04-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/deepseek-v4-flash-0423/
Full dataset: https://llmprice.gitlab.io/data/catalog.json