DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Flash 0731
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on October 22, 2026· 222 models
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 1 M tokens
- Max output
- ▲393 K
- Input, $ per 1M tokens
- ▲$0.300
- Output, $ per 1M tokens
- ▲$1.20
- Cache read, $ per 1M
- $0.006
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- ▲10/17/2026
- Knowledge cutoff
- 2025-05
- API id
- deepseek/deepseek-v4.1-flash-1017
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 1 M tokens
- Max output
- 131 K
- Input, $ per 1M tokens
- $0.440
- Output, $ per 1M tokens
- $1.32
- Cache read, $ per 1M
- $0.014
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 07/31/2026
- Knowledge cutoff
- 2025-05
- API id
- deepseek/deepseek-v4-flash-0731
Which is the better API choice: DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Flash 0731?
- DeepSeek V4.1 Flash 1017: cheapest input (32% less than DeepSeek V4 Flash 0731)
- DeepSeek V4.1 Flash 1017: cheapest output
- DeepSeek V4.1 Flash 1017: the newest (10/17/2026)
DeepSeek V4.1 Flash 1017 costs 32% less on input and 9% less on output than DeepSeek V4 Flash 0731 ($0.300 / $1.20 versus $0.440 / $1.32 per million tokens). All accept 1 M tokens of context. On capabilities, DeepSeek V4.1 Flash 1017 accepts images.
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
With DeepSeek V4.1 Flash 1017 you save $2.58 a month versus DeepSeek V4 Flash 0731 (22% less).
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Clip Preview Google$0.00
- 2Lyria 3 Pro Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4Qwen3.5-9B Qwen$1.72
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Paste your prompt: tokens and cost per model
Rough estimate (about 4 characters per token). Nothing is sent to any server.
Cost of sending it 1,000 times (input only)
- 1Claude Haiku 5.5 Anthropic$0.008
- 2DeepSeek V4.1 Flash 1017 DeepSeek$0.023
- 3DeepSeek V4 Flash 0731 DeepSeek$0.033
- 4Claude Sonnet 5.5 Anthropic$0.152
- 5Claude Sonnet 5 Anthropic$0.152
- 6Claude Opus 5.5 Anthropic$0.304
- 7Claude Opus 5 Anthropic$0.380
- 8Claude Fable 5.1 Anthropic$0.760
Popular comparisons
- Claude Haiku 5.5 vs GPT-6.1 Sol
- Claude Haiku 5.5 vs Gemini 4 Argon
- Claude Haiku 5.5 vs DeepSeek V4.1 Flash 1017
- Claude Haiku 5.5 vs Grok 4.7
- GPT-6.1 Sol vs Gemini 4 Argon
- GPT-6.1 Sol vs DeepSeek V4.1 Flash 1017
- GPT-6.1 Sol vs Grok 4.7
- Gemini 4 Argon vs DeepSeek V4.1 Flash 1017
- Gemini 4 Argon vs Grok 4.7
- DeepSeek V4.1 Flash 1017 vs Grok 4.7
Frequently asked questions
Which is the better API choice: DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Flash 0731?
DeepSeek V4.1 Flash 1017 costs 32% less on input and 9% less on output than DeepSeek V4 Flash 0731 ($0.300 / $1.20 versus $0.440 / $1.32 per million tokens). All accept 1 M tokens of context. On capabilities, DeepSeek V4.1 Flash 1017 accepts images.
Which is cheaper: DeepSeek V4.1 Flash 1017 and DeepSeek V4 Flash 0731?
DeepSeek V4.1 Flash 1017 is cheaper: $0.300 per million input tokens and $1.20 per million output tokens, versus $0.440 / $1.32 for DeepSeek V4 Flash 0731.
Which has more context: DeepSeek V4.1 Flash 1017 and DeepSeek V4 Flash 0731?
DeepSeek V4.1 Flash 1017 and DeepSeek V4 Flash 0731 accept the same context: 1 M tokens.
Which is newer: DeepSeek V4.1 Flash 1017 and DeepSeek V4 Flash 0731?
DeepSeek V4.1 Flash 1017 was released on 10/17/2026; DeepSeek V4 Flash 0731 on 07/31/2026.
What would 10,000 requests a month cost with DeepSeek V4.1 Flash 1017 and DeepSeek V4 Flash 0731?
With 1,500 input and 400 output tokens per request: DeepSeek V4.1 Flash 1017: $9.30; DeepSeek V4 Flash 0731: $11.88 a month, at list price.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.