qwen3-235b-a22b-2507 by deepinfra - AI Model Details, Pricing, and Performance Metrics

qwen
qwen3-235b-a22b-2507
qwen

qwen3-235b-a22b-2507

completions
On:deepinfraparasail

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.

ProviderInputOutput
deepinfra
deepinfra
$0.13 / 1M tokens$0.6 / 1M tokens
parasail
parasail
$0.15 / 1M tokens$0.85 / 1M tokens
Released
Apr 29, 2025
Knowledge
Oct 31, 2024
Context
262144
Input
$0.13 / 1M tokens
Output
$0.6 / 1M tokens
Capabilities: tools
Accepts: text
Returns: text

Access qwen3-235b-a22b-2507 through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-235b-a22b-2507 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Available from 2 providers
Provider:

Category Scores

Benchmark Tests

View Other Benchmarks
AIME
32.7
Mathematics
AA Coding Index
32.1
Programming
AAII
29.9
General
AA Math Index
23.7
Mathematics
GPQA
61.3
STEM (Physics, Chemistry, Biology)
HLE
4.7
General Knowledge
LiveCodeBench
34.3
Programming
MATH-500
90.2
Mathematics
MMLU
87.8
General Knowledge
MMLU-Pro
76.2
General Knowledge
SciCode
29.9
Scientific

Code Examples

Integration samples and API usage