API pricing per million tokens
qwen3-30b-a3b-thinking-2507 Open weightsChecked 6h ago
- Input
- $0.2
- per 1M, list
- Output
- $2.4
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 82K
- 33K max output
Where to buy it (1)
Qwen (Alibaba) (list)the lab's own API$0.2 / $2.4$0.75 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $68.00 direct.
Helicone$68.00+0%
Kong AI Gateway$68.00+0%
LiteLLM$68.00+0%
Vercel AI Gateway$68.00+0%
AWS Bedrock$68.00+0%
Azure AI Foundry$68.00+0%
Google Vertex AI$68.00+0%
Databricks Mosaic AI$68.00+0%
Hugging Face Inference$68.00+0%
Cloudflare AI Gateway$71.40+5%
Requesty$71.40+5%
Eden AI$71.74+5.5%
OpenRouter$71.74+5.5%
Snowflake Cortex AI$81.60+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About Qwen3 30B A3B Thinking 2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.75 per 1M tokens at 3 input to 1 output.
Across fru.devCompany profile
Questions
How much does Qwen3 30B A3B Thinking 2507 cost?
$0.2 per million input tokens and $2.4 per million output tokens.
What is the context window of Qwen3 30B A3B Thinking 2507?
82K tokens, with up to 33K tokens of output.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.