DeepSeek: DeepSeek V4 Flash 0423
DeepSeekOpen weights
DeepSeek: DeepSeek V4 Flash 0423 by DeepSeek costs $0.09 per 1M input tokens and $0.18 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.09
Output (per 1M tokens)
$0.18
Cached input (per 1M)
$0.02
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| openrouter | $0.09 | $0.18 |
| DeepSeek | $0.15 | $0.60 |
Specifications
- Provider
- DeepSeek
- Context window
- 1M tokens
- Parameters
- 284B
- Released
- Apr 2026
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- deepseek-ai/DeepSeek-V4-Flash
Benchmarks
- GPQA Diamond
- 91.0
- LiveBench
- 65.5
- LMArena WebDev Elo
- 1581.6
Speed & latency
Time to first token
0.76s
Output speed
336 tok/s
Fastest host: baseten (via vercel-ai-gateway).
Compare DeepSeek: DeepSeek V4 Flash 0423 with…
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen Turbo$0.20/1MDeepSeek: DeepSeek V4 Flash 0423 vs Laguna XS.2$0.20/1MDeepSeek: DeepSeek V4 Flash 0423 vs Qwen3 4B Instruct$0.20/1MDeepSeek: DeepSeek V4 Flash 0423 vs Yi Lightning$0.20/1MDeepSeek: DeepSeek V4 Flash 0423 vs Llama 3.2 1B Instruct$0.20/1MDeepSeek: DeepSeek V4 Flash 0423 vs mistral-7b-instruct-v0.2$0.22/1M
FAQ
How much does DeepSeek: DeepSeek V4 Flash 0423 cost?
DeepSeek: DeepSeek V4 Flash 0423 is priced at $0.09 per 1M input tokens and $0.18 per 1M output tokens. Output tokens cost more than input.
What is DeepSeek: DeepSeek V4 Flash 0423's context window?
DeepSeek: DeepSeek V4 Flash 0423 supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is DeepSeek: DeepSeek V4 Flash 0423 open weight?
Yes — DeepSeek: DeepSeek V4 Flash 0423 has openly available weights.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.