Model reference · Synced 2025-04-29
DeepSeek V4 Flash
DeepSeek V4 Flash is an AI model from Cortecs. 1M context window. Capabilities: reasoning, tool calling, open weights. Available on 13 providers. Cheapest listing: $0.133 input / $0.266 output per 1M tokens.
Quick facts
- Cheapest input: $0.133 per 1M tokens (Cortecs)
- Cheapest output: $0.266 per 1M tokens
- Context window: 1M tokens
- Max output: 384K tokens
- Release date: 2026-04-24
- Knowledge cutoff: 2025-05
- Capabilities: reasoning, tool calling, open weights
- Provider count: 13
Provider pricing
Same model, different providers, different prices. Cheapest first.
| Provider | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Cortecs | $0.133 | $0.266 | 1M | 2026-04-24 |
| DeepSeek | $0.14 | $0.28 | 1M | 2026-04-24 |
| OpenRouter | $0.14 | $0.28 | 1M | 2026-04-24 |
| OpenCode Go | $0.14 | $0.28 | 1M | 2026-04-24 |
| Alibaba (China) | $0.14 | $0.28 | 1M | 2026-04-24 |
| ZenMux | $0.14 | $0.28 | 1M | 2026-04-24 |
| NovitaAI | $0.14 | $0.28 | 1M | 2026-04-24 |
| Deep Infra | $0.14 | $0.28 | 1M | 2026-04-24 |
| Nvidia | $0.14 | $0.28 | 1M | 2026-04-24 |
| Vercel AI Gateway | $0.14 | $0.28 | 1M | 2026-04-23 |
| LLM Gateway | $0.14 | $0.28 | 1M | 2026-04-24 |
| AIHubMix | $0.154 | $0.308 | 1M | 2026-04-24 |
| Venice AI | $0.17 | $0.35 | 1M | 2026-04-24 |
Prices synced daily from models.dev + provider docs.
How to use this model
If you're picking DeepSeek V4 Flash for a project, the three things that matter most:
- Compare it side-by-side with one or two alternatives in the live comparison tool. Pricing differences matter more than benchmarks at scale.
- Pick the cheapest provider that meets your latency / SLA need. Big spread across providers for the same weights.
- Re-evaluate every 3 months. Frontier prices drop fast; a model that's cheapest today may not be in a quarter.
Related models
FAQ
How much does DeepSeek V4 Flash cost? $0.133 input / $0.266 output per 1M tokens at the cheapest listing. See the table above for other providers.
What is the context window? 1M tokens.
Which providers offer it? DeepSeek, OpenRouter, OpenCode Go, Alibaba (China), ZenMux, NovitaAI, Deep Infra, Venice AI, AIHubMix, Nvidia, and others — see the full table above.
Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.