Discord

Compare · Leaderboard

qwen

qwen3 30b a3b Thinking 2507

Model id: qwen/qwen3-30b-a3b-thinking-2507

Context: 131K tokens

Tool callingJSON mode
Route this with model=auto

Price per 1M tokens

Input $0.2/M · Output $2.4/M

+ VideoRouter platform fee: 2.5% of provider cost (≈ $0.005/M in · $0.06/M out) — billed as its own line, never blended into the price above.

Hosts

Don’t know how to select a host? Check Provider selection.

HostContextInput $/MOutput $/M
qwen 131K $0.2/M $2.4/M
qwen-eu 131K $0.2/M $2.4/M

Served through qwen's API — 0% additional markup beyond our 2.5% platform fee. Other rows above are the same model through a different host — click one to switch.

Capability profile

Reasoning○○○○○0/5
Coding○○○○○0/5
Quality○○○○○0/5

Not yet graded — this model isn't in Artificial Analysis's evaluated catalog, so it carries no capability score and is never chosen by auto-routing (still servable by requesting its exact model name). See the leaderboard for models with real benchmark data.

API

curl https://videorouter.sh/api/v1/chat/completions \
  -H "Authorization: Bearer llmr_sk_..." \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen/qwen3-30b-a3b-thinking-2507", "messages": [{"role": "user", "content": "Hello!"}]}'