DeepSeek V4.1 Flash 1017 Thinking
NanoGPTOpen weights
DeepSeek V4.1 Flash 1017 Thinking by NanoGPT costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.15
Output (per 1M tokens)
$0.60
Cached input (per 1M)
$0.00
Specifications
- Provider
- NanoGPT
- Context window
- 1M tokens
- Parameters
- —
- Released
- Oct 2026
- Open weights
- Yes
- Frontier model
- No
Compare DeepSeek V4.1 Flash 1017 Thinking with…
DeepSeek V4.1 Flash 1017 Thinking vs DeepSeek V4.1 Flash$0.60/1MDeepSeek V4.1 Flash 1017 Thinking vs GPT OSS 120B$0.60/1MDeepSeek V4.1 Flash 1017 Thinking vs GPT-4o-mini$0.60/1MDeepSeek V4.1 Flash 1017 Thinking vs Command R (08-2024)$0.60/1MDeepSeek V4.1 Flash 1017 Thinking vs Gemma 4 26B A4B IT$0.60/1MDeepSeek V4.1 Flash 1017 Thinking vs Mistral Small (latest)$0.60/1M
FAQ
How much does DeepSeek V4.1 Flash 1017 Thinking cost?
DeepSeek V4.1 Flash 1017 Thinking is priced at $0.15 per 1M input tokens and $0.60 per 1M output tokens. Output tokens cost more than input.
What is DeepSeek V4.1 Flash 1017 Thinking's context window?
DeepSeek V4.1 Flash 1017 Thinking supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is DeepSeek V4.1 Flash 1017 Thinking open weight?
Yes — DeepSeek V4.1 Flash 1017 Thinking has openly available weights.
Data as of 2026-10-18. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.