Qwen 3 30B (MoE) — pricing & specs
Qwen 3 30B (MoE) is a balanced model from Alibaba, at capability tier 2 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-06-13.
$/M-token pricing
as of 2026-06-13 · OpenRouter (lowest)What Qwen 3 30B (MoE) costs in practice
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $0.620 |
| A 10K-token request (8K in / 2K out) | $0.0020 |
| 1,000 agent runs (~2K in / 500 out each) | $0.490 |
| 1M-token RAG chat session (900K cached in / 100K out) | $0.158 |
Estimated from list price (as of 2026-06-13) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- Alibaba
- Family
- Qwen 3
- Capability tier
- 2 / 8
- Size class
- BALANCED
- Category
- GENERAL
- Parameters
- 30B total · 3B active (MoE)
- Context window
- 131,072 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference NVIDIA Rubin Ultra VR300 at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 2
Same capability tier, sorted by output price — the cheaper-capable options.
- LLaMA 3 8BMetaopen/M out
- Gemma 3 12BGoogleopen/M out
- Mistral 7BMistralopen/M out
- Llama 3.1 8BMetaopen/M out
FAQ
How much does Qwen 3 30B (MoE) cost per token?
Qwen 3 30B (MoE) costs $0.12 per million input tokens and $0.50 per million output tokens, via OpenRouter (lowest), as of 2026-06-13.
What does a typical request with Qwen 3 30B (MoE) cost?
At list price, a 10K-token request (8K in / 2K out) with Qwen 3 30B (MoE) costs about $0.0020, and 1,000 agent runs (~2K in / 500 out each) about $0.490.
What is Qwen 3 30B (MoE)'s context window?
Qwen 3 30B (MoE) supports a 131,072-token context window.
What capability tier is Qwen 3 30B (MoE)?
Qwen 3 30B (MoE) sits at capability tier 2 of 8 on the Mintok scale (BALANCED size class).
Is Qwen 3 30B (MoE) open-source or proprietary?
Qwen 3 30B (MoE) is a proprietary model from Alibaba, accessed via API.
Put Qwen 3 30B (MoE) to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.