DeepSeek V4.1 Flash 1017:thinking API
DeepSeek's DeepSeek V4.1 Flash 1017:thinking costs $0.27 to $0.405 per million input tokens and $0.012 to $1 per million output tokens from 2 suppliers. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send deepseek-v4.1-flash-1017:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About DeepSeek V4.1 Flash 1017:thinking
DeepSeek V4.1 Flash 1017:thinking is a language model from DeepSeek. Its release date is 17 October 2026. October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding. Its weights are open. Its licence is MIT. Its training data ends in May 2025. It takes text and images and gives text. The largest offer takes 1,048,576 input tokens. One job can generate up to 131,072 tokens. It scores 32.6 on the Artificial Analysis Intelligence Index, #17 of 64 scored models on this exchange. It has 2 suppliers on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- deepseek-v4.1-flash-1017:thinking
- Maker
- DeepSeek
- Context window
- 1M tokens
- Input price
- $0.27 to $0.405 per million tokens
- Output price
- $0.012 to $1 per million tokens
- Suppliers
- 2 suppliers
- Regions
- global, us
Providers
- Munito AI: global, declared precision fp8, $0.27 input and $1 output per million tokens, $0.0054 cache read per million tokens, 1M tokens of context
- Pera: us, declared precision fp8, $0.405 input and $0.012 output per million tokens, $0.405 cache read per million tokens, $0.0116 fee for each request, 1M tokens of context
Scores
- Intelligence: 32.6, #17 of 64
- HLE: 43.3, #33 of 465
- AA-LCR: 82.7, #28 of 409
- SciCode: 55.9, #32 of 178
- SimpleQA Verified: 42.5, #57 of 172
Scores: Artificial Analysis (https://artificialanalysis.ai/)
Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash-1017:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is DeepSeek V4.1 Flash 1017:thinking?
- DeepSeek V4.1 Flash 1017:thinking is a language model from DeepSeek. Its release date is 17 October 2026. October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding. Its weights are open. Its licence is MIT. Its training data ends in May 2025.
- How much does DeepSeek V4.1 Flash 1017:thinking cost?
- Offers now ask $0.27 to $0.405 per million input tokens and $0.012 to $1 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of DeepSeek V4.1 Flash 1017:thinking?
- The largest offer takes 1,048,576 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can DeepSeek V4.1 Flash 1017:thinking do?
- Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Log probabilities, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does DeepSeek V4.1 Flash 1017:thinking support?
- Text · Images → Text.
- Which providers serve DeepSeek V4.1 Flash 1017:thinking?
- It has 2 suppliers now, with 2 offers. The table above ranks them by the cost of one agent-mix job.
- How do I call DeepSeek V4.1 Flash 1017:thinking?
- Send "deepseek-v4.1-flash-1017:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was DeepSeek V4.1 Flash 1017:thinking released?
- Its creator released it on 17 October 2026.
- When was DeepSeek V4.1 Flash 1017:thinking listed?
- The exchange first listed it on 10/17/2026. This is not its release date.
Related pages
- DeepSeek V4 Flash 0731
- DeepSeek V4 Flash
- DeepSeek V4.1 Flash:thinking
- DeepSeek V4.1 Flash
- DeepSeek V4 Pro
- DeepSeek V4.1 Flash 1017
- Deepseek
- Popular open weights
- Reasoning models
- Set up a client
- All models
- Providers
- Discover the best model for your budget
- Quickstart
- llms.txt: the index of every page, as Markdown
- llms-full.txt: every page in one file
- This page as Markdown