Qwen3-235B-A22B-Thinking-2507 API
About
Build advanced reasoning agents with Qwen3-235B-A22B-Thinking-2507, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.10/1M input and $0.10/1M output tokens, native tool calling support, open weights architecture. Access Qwen3-235B-A22B-Thinking-2507 via the Weights & Biases API with up to 262K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
262K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.10
Output
$0.10
Frequently Asked Questions
Qwen3-235B-A22B-Thinking-2507 by Weights & Biases costs $0.10 per 1M input tokens and $0.10 per 1M output tokens.
Model Details
ID
Qwen/Qwen3-235B-A22B-Thinking-2507
Provider
Weights & BiasesFamily
qwen
Release Date
Jul 25, 2025
Knowledge Cutoff
Apr 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
WANDB_API_KEY
API Base URL
https://api.inference.wandb.ai/v1