← All modelsQwen — served by Reka

Qwen3.6 35B A3B

Open-weight 35B MoE (3B active) — thinking, tools, image input, 262K context — self-hosted.

Qwen — served by Reka$0.15 in · $1.00 out / 1M tokens (≤256K ctx)llmqwenopen-weightsmultimodal
Capabilities
llmqwenopen-weightsmultimodal
Pricing
Context bandMax tokensInput / M tokOutput / M tok
≤256K262,144$0.15$1.00
API

Wire it up.

EndpointPOST https://api.tryinfer.com/v1/chat/completions
request
curl https://api.tryinfer.com/v1/chat/completions \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.6-35b-a3b",
"messages": [{ "role": "user", "content": "Summarize the trade-offs between dense and mixture-of-experts models in three bullets." }]
}'

OpenAI-compatible — point your SDK at Infer with a bearer token. Get an API key →