DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Cheapest input
$0.09
$/MTok · models.dev
Cheapest output
$0.18
$/MTok
Context
1.0M
tokens
Offers
12
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek-ai/DeepSeek-V4-Flash | DeepInfra | $0.09 | $0.18 | $0.018 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Pioneer | $0.1 | $0.2 | $0.0197 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | GMI Cloud | $0.112 | $0.224 | $0.022 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Abacus | $0.14 | $0.28 | $0.03 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Hugging Face | $0.14 | $0.28 | $0 | 1.0M |
| models.devdeepseek-ai/deepseek-v4-flash | NVIDIA | $0.14 | $0.28 | $0.0028 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | SiliconFlow (China) | $0.14 | $0.28 | $0.003 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | SiliconFlow | $0.14 | $0.28 | $0.028 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Weights & Biases | $0.14 | $0.28 | $0.07 | 1.0M |
| LiteLLMdeepseek-ai/DeepSeek-V4-Flash | — | $0.14 | $0.28 | $0 | — |
| models.devdeepseek-ai/deepseek-v4-flash | Ai& | $0.15 | $0.25 | $0 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Vultr | $0.3 | $1 | $0 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-05Released: 2026-04-24Family: deepseek-flash