Compare · Leaderboard

qwen

qwen3 VL 235b a22b Thinking

Canonical id: qwen/qwen3-vl-235b-a22b-thinking · Context: 131K tokens

VisionTool callingJSON mode
Route this with model=auto

Price per 1M tokens

Input $0.4/M · Output $4/M

+ LLMRouter platform fee: 1% of provider cost (≈ $0.004/M in · $0.04/M out) — billed as its own line, never blended into the price above.

Providers

ProviderContextInput $/MOutput $/M
qwen (viewing) 131K $0.4/M $4/M
qwen-eu 131K $0.4/M $4/M
novita 131K $0.98/M $3.95/M

Served through qwen's API — 0% additional markup beyond our 1% platform fee. Other rows above are the same model through a different provider — click one to switch.

Capability profile

Reasoning●●○○○2/5
Coding●●○○○2/5
Quality●●○○○2/5

Derived from Artificial Analysis's licensed Intelligence/Coding Index — see the leaderboard for their full, independently measured scores. Source: Artificial Analysis.

API

curl https://api.llmrouter.sh/v1/chat/completions \
  -H "Authorization: Bearer llmr_sk_..." \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3-vl-235b-a22b-thinking", "messages": [{"role": "user", "content": "Hello!"}]}'