Model prices / Alibaba / Qwen3 30B A3B Instruct 2507
Qwen3 30B A3B Instruct 2507Open weights
Alibaba · released 2025-07-28
No price from the maker itself is on record for Qwen3 30B A3B Instruct 2507. The lowest of 14 providers is Ambient: $0.09 per 1M input tokens and $0.3 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 16.4K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
AAmbientLowestqwen/ | $0.09 | $0.3 | $0.09 | Lowest | Official docs |
 SiliconFlowQwen/ | $0.09 | $0.3 | — | Official docs | |
CCortecsqwen3-30b-a3b-instruct-2507 | $0.099 | $0.299 | — | Official docs | |
EEden AInebius/ | $0.1 | $0.3 | $0.1 | Official docs | |
KKilo Gatewayqwen/ | $0.1 | $0.3 | $0.1 | Official docs | |
 Nebius Token FactoryQwen/ | $0.1 | $0.3 | $0.1 | Official docs | |
 OpenRouterqwen/ | $0.1 | $0.3 | $0.1 | Official docs | |
| SiliconFlow (China)Qwen/ | $0.104613 | $0.418453 | — | Official docs | |
PPrime Inferenceqwen/ | $0.13 | $0.52 | — | Official docs | |
NNanoGPTqwen/ | $0.2 | $0.5 | $0.1 | Official docs | |
CClarifaiqwen/ | $0.3 | $0.5 | — | Official docs | |
QQiniuDeprecatedqwen3-30b-a3b-instruct-2507 | $0.108696 | $0.434783 | — | Deprecated | Official docs |
2 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 LMStudioqwen/ | $0 | $0 | — | Official docs | |
 ModelScopeQwen/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Qwen instruction model for multilingual chat, reasoning, and tool use
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 16.4K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2025-07-28
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.