Qwen 3.6 35B a3b:thinking API
Alibaba's Qwen 3.6 35B a3b:thinking costs $0.112 per million input tokens and $0.799 per million output tokens from 1 supplier. 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 qwen3.6-35b-a3b: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 Qwen 3.6 35B a3b:thinking
Qwen 3.6 35B a3b:thinking is a language model from Alibaba. Its release date is 17 April 2026. Open multimodal Qwen MoE for local agents that need vision, audio, and code. Its weights are open. It takes text, images and video and gives text. The largest offer takes 1,048,576 input tokens. It has 1 supplier on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- qwen3.6-35b-a3b:thinking
- Maker
- Alibaba
- Context window
- 1M tokens
- Input price
- $0.112 per million tokens
- Output price
- $0.799 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $0.112 input and $0.799 output per million tokens, $0.0559 cache read per million tokens, 1M tokens of context
Scores
- HLE: 22.2, #155 of 465
- GPQA: 84.1, #115 of 432
- AA-LCR: 71.7, #154 of 409
- SciCode: 36.6, #143 of 178
- Terminal-Bench Hard: 34.8, #63 of 311
- τ²-Bench: 95.3, #32 of 313
- IFBench: 64.4, #87 of 321
- SimpleQA Verified: 15.9, #151 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": "qwen3.6-35b-a3b:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Qwen 3.6 35B a3b:thinking?
- Qwen 3.6 35B a3b:thinking is a language model from Alibaba. Its release date is 17 April 2026. Open multimodal Qwen MoE for local agents that need vision, audio, and code. Its weights are open.
- How much does Qwen 3.6 35B a3b:thinking cost?
- Offers now ask $0.112 per million input tokens and $0.799 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 Qwen 3.6 35B a3b:thinking?
- The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Qwen 3.6 35B a3b:thinking do?
- Its providers list Vision, Video input, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Qwen 3.6 35B a3b:thinking support?
- Text · Images · Video → Text.
- Which providers serve Qwen 3.6 35B a3b:thinking?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call Qwen 3.6 35B a3b:thinking?
- Send "qwen3.6-35b-a3b:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Qwen 3.6 35B a3b:thinking released?
- Its creator released it on 17 April 2026.
- When was Qwen 3.6 35B a3b:thinking listed?
- The exchange first listed it on 10/10/2026. This is not its release date.
Related pages
- Qwen 3.8 27B
- Qwen 3.6 35B a3b
- Qwen 3 14B
- Qwen 3 5 4B
- Qwen 3.5 9B
- Qwen 2.5 7B Instruct
- 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