API pricing per million tokens
qwen3-235b-a22b-thinking-2507 Open weightsChecked 6h ago
- Input
- $0.23
- per 1M, list
- Output
- $2.3
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 131K
- 118K max output
Where to buy it (3)
Qwen (Alibaba) (list)the lab's own API$0.23 / $2.3$0.747 blended
Novita AIfp8, fp8+30%$0.3 / $3$0.975 blended
Venicefp8, fp8+62%$0.45 / $3.5$1.21 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $69.00 direct.
Helicone$69.00+0%
Kong AI Gateway$69.00+0%
LiteLLM$69.00+0%
Vercel AI Gateway$69.00+0%
AWS Bedrock$69.00+0%
Azure AI Foundry$69.00+0%
Google Vertex AI$69.00+0%
Databricks Mosaic AI$69.00+0%
Hugging Face Inference$69.00+0%
Cloudflare AI Gateway$72.45+5%
Requesty$72.45+5%
Eden AI$72.80+5.5%
OpenRouter$72.80+5.5%
Snowflake Cortex AI$82.80+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 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.747 per 1M tokens at 3 input to 1 output.
Across fru.devCompany profile
Questions
How much does Qwen3 235B A22B Thinking 2507 cost?
$0.23 per million input tokens and $2.3 per million output tokens.
What is the context window of Qwen3 235B A22B Thinking 2507?
131K tokens, with up to 118K tokens of output.
Where is Qwen3 235B A22B Thinking 2507 cheapest?
Of 3 routes tracked, Qwen (Alibaba) is cheapest at $0.23 input and $2.3 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.