Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads
DeepSeek V4 Flash 0423 is offered by 4 providers on this page. Its reference price is $0.19 per 1M input tokens and $0.51 per 1M output tokens. The lowest paid channel is Venice AI at $0.138 / $0.275 per 1M, about 1.4× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 131,072 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-05.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Venice AI deepseek-v4-flash | Gateway | $0.14 | $0.28 | $0.028 | — | 1,000,000 | 32,768 | |
| Merge Gateway | Gateway | $0.14 | $0.28 | — | — | 131,072 ⚠ | 32,768 | |
| NanoGPT | Gateway | $0.14 | $0.28 | $0.03 | — | 1,048,576 ⚠ | 384,000 | |
| Ofox | Gateway | $0.19 | $0.51 | $0.028 | — | 1,000,000 | 384,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 4 providers.