Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Qwen3 30B A3B by alibaba is offered by 12 providers on this page. Public prices are shown for 11 of them. Its reference price is $0.11 per 1M input tokens and $1.08 per 1M output tokens. The lowest paid channel is Helicone at $0.08 / $0.29 per 1M, about 1.6× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 7.6 on the Intelligence Index. Against its lowest blended price of $0.133 per 1M, that is roughly 57 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 109 tokens per second, with 2.19s to the first token.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 40,000 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Helicone | Gateway | $0.08 | $0.29 | — | — | 41,000 ⚠ | 41,000 | |
| NanoGPT | Gateway | $0.10 | $0.30 | $0.05 | — | 41,000 ⚠ | 32,768 | |
| NovitaAI qwen/qwen3-30b-a3b-fp8 | Gateway | $0.09 | $0.45 | — | — | 40,960 ⚠ | 20,000 | |
| Jiekou.AI qwen/qwen3-30b-a3b-fp8 | Gateway | $0.09 | $0.45 | — | — | 40,960 ⚠ | 20,000 | |
| Deep Infra Qwen/Qwen3-30B-A3B | Cloud | $0.12 | $0.50 | — | — | 40,960 ⚠ | 16,384 | |
| OpenRouter | Gateway | $0.12 | $0.50 | — | — | 131,072 ⚠ | 16,384 | |
| Hugging Face Qwen/Qwen3-30B-A3B | Cloud | $0.12 | $0.50 | — | — | 40,960 ⚠ | 16,384 | |
| Vercel AI Gateway alibaba/qwen-3-30b | Cloud | $0.12 | $0.50 | — | — | 40,960 ⚠ | 16,384 | |
| Kilo Gateway | Gateway | $0.13 | $0.52 | — | — | 40,960 ⚠ | 16,384 | |
| Merge Gateway | Gateway | $0.11 | $1.08 | $0.022 | — | 131,072 ⚠ | 32,768 | |
| 302.AI | Gateway | $0.11 | $1.08 | — | — | 128,000 | 8,192 | |
| Qiniu | Gateway | — | — | — | — | 40,000 ⚠ | 4,096 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
4 / 12 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.