Qwen3 30B A3B (greenference)
by LLM Gateway · family qwen · listed Apr 2025W
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Current rates USD per 1M tokens
Input$0.076
Output$0.228
Cache read—
Cache write—
Against the market
On the record
- Model id
greenference/qwen3-30b-a3b- Context window
- 8K tokens
- Max output
- 4K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-04-28
- Last updated
- 2025-04-28
- Provider docs
- llmgateway.io/docs
Back of the envelope
≈
Also listed at
- DevPass (LLM Gateway)$0.076 in · $0.228 out
- Helicone$0.08 in · $0.29 out
- Merge Gateway$0.108 in · $1.08 out
- Qiniu$0.109 in · $0.435 out
- 302.AI$0.11 in · $1.08 out
- Kilo Gateway$0.12 in · $0.50 out
- OpenRouter$0.12 in · $0.50 out
- Hugging Face$0.12 in · $0.50 out
- Deep Infra$0.12 in · $0.50 out
- NanoGPT$0.12 in · $0.50 out