Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507 is a text model from DeepInfra with a context window of 262K tokens and max output of 262K tokens. Pricing starts at 0.30 per million input tokens and 2.90 per million output tokens (cheapest at OpenRouter).

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keydeepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507
ProviderDeepInfra
Provider IDdeepinfra
ModeText
Canonical Nameqwen-thinking-3-235b-a22b-2507
Context Window262K tokens
Max Output262K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0003000.300
Output Tokens0.00292.90

Benchmarks

Intelligence Index39.9#29
Coding Index30.5#38
GPQA0.9#14
HLE0.3#16
IFBench0.7#22
Time to First Token1.78s#206
SciCode0.4#21
LCR0.7#19
TerminalBench Hard0.2#41
TAU20.8#27

Price Comparison by Provider

Compare prices for Qwen3 235B A22B Thinking 2507 across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
Weights & Biaseswandb/Qwen/Qwen3-235B-A22B-Thinking-25070.0100.010
Together AItogether_ai/Qwen/Qwen3-235B-A22B-Thinking-25070.6503.00
OpenRouteropenrouter/qwen/qwen3-235b-a22b-thinking-25070.1100.600
DeepInfradeepinfra/Qwen/Qwen3-235B-A22B-Thinking-25070.3002.90

All Variants

All available versions, regions, and API endpoints for Qwen3 235B A22B Thinking 2507.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507DeepInfraText0.3002.90262K262Knoyes
openrouter/qwen/qwen3-235b-a22b-thinking-2507OpenRouterText0.1100.600262K262Knoyes
together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507Together AIText0.6503.00256KN/Anoyes
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507Weights & BiasesText0.0100.010262K262Knono