DeepSeek V4 Flash 0731 (Sference)
Eden AIOpen weights
DeepSeek V4 Flash 0731 (Sference) by Eden AI costs $0.28 per 1M input tokens and $0.56 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.28
Output (per 1M tokens)
$0.56
Cached input (per 1M)
$0.07
Specifications
- Provider
- Eden AI
- Context window
- 1M tokens
- Parameters
- —
- Released
- Jul 2026
- Open weights
- Yes
- Frontier model
- No
Compare DeepSeek V4 Flash 0731 (Sference) with…
DeepSeek V4 Flash 0731 (Sference) vs inclusionAI/Ling-flash-2.0$0.57/1MDeepSeek V4 Flash 0731 (Sference) vs Qwen3 235B A22B Instruct 2507$0.55/1MDeepSeek V4 Flash 0731 (Sference) vs DeepSeek V4 Flash Latest$0.53/1MDeepSeek V4 Flash 0731 (Sference) vs Hy3$0.53/1MDeepSeek V4 Flash 0731 (Sference) vs GPT OSS 120B$0.60/1MDeepSeek V4 Flash 0731 (Sference) vs GPT-4o-mini$0.60/1M
FAQ
How much does DeepSeek V4 Flash 0731 (Sference) cost?
DeepSeek V4 Flash 0731 (Sference) is priced at $0.28 per 1M input tokens and $0.56 per 1M output tokens. Output tokens cost more than input.
What is DeepSeek V4 Flash 0731 (Sference)'s context window?
DeepSeek V4 Flash 0731 (Sference) 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 (Sference) open weight?
Yes — DeepSeek V4 Flash 0731 (Sference) has openly available weights.
Data as of 2026-10-22. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.