DeepSeek V4 Flash (1-flash-1017) pricing & specs
DeepSeek · released 2026-10-17 · ● verified 2026-10-23 · deprecated
This model is deprecated. Cheapest compatible replacement: Qwen3.7 Flash.
DeepSeek V4 Flash (1-flash-1017) is a DeepSeek model released on 2026-10-17. At $0.15 per million input tokens and $0.60 per million output tokens, its blended price of $0.2625 per 1M tokens is lower than 71% of the 182 models we track. It offers text and image input, a 1.05M-token context window, built-in reasoning, tool calling and structured output. Its weights are open, and it is available from 4 tracked hosting providers.
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs DeepSeek V4 Flash (1-flash-1017) |
|---|---|---|---|---|
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −79% |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | 1.05M | −52.4% |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | 1.05M | −52.4% |
| Qwen3.5 Flash | $0.10 | $0.40 | 1M | −33.3% |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | −33.3% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| DeepInfra | $0.20 | $0.60 |
| Fireworks AI | $0.21 | $0.84 |
| Baseten | $0.30 | $1.20 |
| Novita AI | $0.30 | $1.20 |
// embed this price badge
Show the live price of DeepSeek V4 Flash (1-flash-1017) in your README or docs (updated daily):
[](https://aisignals.dev/models/deepseek/deepseek-v4.1-flash-1017)
// faq
How much does DeepSeek V4 Flash (1-flash-1017) cost?
DeepSeek V4 Flash (1-flash-1017) costs $0.15 per million input tokens and $0.60 per million output tokens. At 50M input and 10M output tokens per month that is about $13.50.
What is the context window of DeepSeek V4 Flash (1-flash-1017)?
1.05M tokens, with up to 393.2K output tokens per request.
Does DeepSeek V4 Flash (1-flash-1017) support prompt caching?
Yes. Cached input tokens cost $0.003 per million.
What are cheaper alternatives to DeepSeek V4 Flash (1-flash-1017)?
Qwen3.7 Flash ($0.03 in / $0.13 out), Muse Spark 1.2 Contributor ($0.10 in / $0.20 out), Muse Spark 1.3 Contributor ($0.10 in / $0.20 out) offer the same input types and capabilities for less.
Is DeepSeek V4 Flash (1-flash-1017) open weights?
Yes. It is available from 4 tracked hosts; the cheapest is DeepInfra at $0.20 input and $0.60 output per million tokens.
// spec sheet
- input / 1M
- $0.15
- output / 1M
- $0.60
- cache read / 1M
- $0.003
- blended (3:1)
- $0.2625
- context
- 1.05M
- max output
- 393.2K
- input types
- text · image
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- 2025-05
- price source
- DeepSeek
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $7.00 |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $7.00 |
| DeepSeek V4 Flash (1-flash-1017) | $0.15 | $0.60 | $13.50 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.