DeepSeek V4 Flash 0731 (Thinking)
NanoGPTOpen weights
DeepSeek V4 Flash 0731 (Thinking) by NanoGPT costs $0.05 per 1M input tokens and $0.16 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.05
Output (per 1M tokens)
$0.16
Cached input (per 1M)
$0.01
Specifications
- Provider
- NanoGPT
- Context window
- 1M tokens
- Parameters
- —
- Released
- Jul 2026
- Open weights
- Yes
- Frontier model
- No
Compare DeepSeek V4 Flash 0731 (Thinking) with…
DeepSeek V4 Flash 0731 (Thinking) vs Gemma 3 12B$0.15/1MDeepSeek V4 Flash 0731 (Thinking) vs Gemma 3 12B IT$0.15/1MDeepSeek V4 Flash 0731 (Thinking) vs Qwen3.5-9B$0.15/1MDeepSeek V4 Flash 0731 (Thinking) vs Pixtral 12B$0.15/1MDeepSeek V4 Flash 0731 (Thinking) vs Open Mistral Nemo$0.15/1MDeepSeek V4 Flash 0731 (Thinking) vs DeepSeek V4 Flash 0423$0.18/1M
FAQ
How much does DeepSeek V4 Flash 0731 (Thinking) cost?
DeepSeek V4 Flash 0731 (Thinking) is priced at $0.05 per 1M input tokens and $0.16 per 1M output tokens. Output tokens cost more than input.
What is DeepSeek V4 Flash 0731 (Thinking)'s context window?
DeepSeek V4 Flash 0731 (Thinking) supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is DeepSeek V4 Flash 0731 (Thinking) open weight?
Yes — DeepSeek V4 Flash 0731 (Thinking) has openly available weights.
Data as of 2026-10-15. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.