All Models
DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Benchmarks
Available Providers (32)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Alibaba Token Plan (China) | deepseek-v4-flash | $0/MTok | $0/MTok | 1M | 384K | |
 Alibaba Token Plan | deepseek-v4-flash | $0/MTok | $0/MTok | 1M | 384K | |
 OpenRouter | deepseek/deepseek-v4-flash | $0.09/MTok | $0.18/MTok | 1M | 65.5K | |
 Deep Infra | deepseek-ai/DeepSeek-V4-Flash | $0.10/MTok | $0.20/MTok | 1.0M | 16.4K | |
 GMI Cloud | deepseek-ai/DeepSeek-V4-Flash | $0.11/MTok | $0.22/MTok | 1.0M | 384K | |
 CrofAI | deepseek-v4-flash | $0.12/MTok | $0.21/MTok | 1M | 131.1K | |
 Cortecs | deepseek-v4-flash | $0.13/MTok | $0.27/MTok | 1.0M | 384K | |
 Venice AI | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 32.8K | |
 Alibaba (China) | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Vercel AI Gateway | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Hugging Face | deepseek-ai/DeepSeek-V4-Flash | $0.14/MTok | $0.28/MTok | 1.0M | 384K | |
 NovitaAI | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.0M | 393.2K | |
 Fireworks AI | accounts/fireworks/models/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Auriko | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 OpenCode Go | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 ZenMux | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 SiliconFlow (China) | deepseek-ai/DeepSeek-V4-Flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Merge Gateway | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 LLM Gateway | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.1M | 384K | |
 Nvidia | deepseek-ai/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.0M | 393.2K | |
 OpenCode Zen | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 SiliconFlow | deepseek-ai/DeepSeek-V4-Flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Kilo Gateway | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.0M | 384K | |
 NanoGPT | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.0M | 384K | |
 DeepSeek | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 Wafer | deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 OrcaRouter | deepseek/deepseek-v4-flash | $0.19/MTok | $0.37/MTok | 1M | 384K | |
 Azure | deepseek-v4-flash | $0.19/MTok | $0.51/MTok | 1M | 384K | |
 routing.run | route/deepseek-v4-flash | $0.49/MTok | $0.74/MTok | 1M | 131.1K | |
 AnyAPI | deepseek/deepseek-v4-flash | —/MTok | —/MTok | 1M | 384K | |
 DigitalOcean | deepseek-4-flash | —/MTok | —/MTok | 262.1K | 8.2K | |
 Ollama Cloud | deepseek-v4-flash | —/MTok | —/MTok | 1.0M | 1.0M |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output