Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

Model weights
Compare

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.

Modalities

In / Out Price

75% off

$0.0875 / $0.35per 1M

Context

262K

Released

Jul 21, 2025

Knowledge Cutoff

Jun 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Qwen: Qwen3 235B A22B Instruct 2507 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisQwen3 235B A22B 2507 Instruct GPQA Diamond75.3%
Artificial AnalysisQwen3 235B A22B 2507 Instruct HLE11.1%
Artificial AnalysisQwen3 235B A22B 2507 Instruct IFBench46.1%
Artificial AnalysisQwen3 235B A22B 2507 Instruct τ²-Bench Telecom33.3%
Artificial AnalysisQwen3 235B A22B 2507 Instruct AA-LCR33.9%
Artificial AnalysisQwen3 235B A22B 2507 Instruct CritPt0.0%
Artificial AnalysisQwen3 235B A22B 2507 Instruct Terminal-Bench Hard15.2%
Artificial AnalysisQwen3 235B A22B 2507 Instruct AA-Omniscience Accuracy18.7%
Artificial AnalysisQwen3 235B A22B 2507 Instruct AA-Omniscience Non-Hallucination Rate22.8%
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena 3D Elo1023
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena Code Categories Elo1054
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena Data Visualization Elo1084
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena Game Development Elo975
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena UI Component Elo981
Design ArenaQwen3-235B-A22B-Instruct-2507 Models Arena Website Elo1070

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
75% off
$0.35$0.0875$1.40$0.350$0.07$0.01751.21s26 tps
99.06%
$0.0900$0.550--0.41s24 tps
97.23%
$0.0900$0.580--0.63s37 tps
98.63%
$0.1400$0.800$0.05000.61s30 tps
99.85%
$0.1495$0.598--0.44s41 tps
100.00%
$0.1500$0.750--0.66s22 tps
97.74%
$0.2000$0.600--0.57s50 tps
98.71%
40% off
$0.35$0.2100$1.40$0.840--0.81s31 tps
99.27%
$0.2200$0.880--0.51s36 tps
99.84%
$0.2500$1.000--0.52s41 tps
99.99%

Throughput

50tok/s

P50, best across providers

Latency

0.41s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.85%

Availability over the last 3 days

Last 72 hours
Availability 99.85%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.83%
Without Routing
96.16%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://github.com/SkyrimNet
SkyrimNet
new
10.5Btokens
2.
Favicon for https://bitsec.ai/
Bitsec
new
6.2Btokens
3.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
4.65Btokens
4.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
2.64Btokens
5.
Favicon for https://librarian.secondf8n.ai/
LibrArIaN
new
2.63Btokens

Frequently asked questions

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.

Qwen3 235B A22B Instruct 2507 costs $0.0875/M input tokens and $0.35/M output tokens, with separate rates for Cache Read at $0.0175/M tokens.

Qwen3 235B A22B Instruct 2507 has a 262,144 token context window.

Yes. Qwen3 235B A22B Instruct 2507 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Qwen3 235B A22B Instruct 2507 is served by 9 providers on OpenRouter: GMICloud, DeepInfra, NovitaAI, Parasail, Alibaba Cloud Int., Venice, Nebius Token Factory, StreamLake and 1 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3 235B A22B Instruct 2507 was released on July 21, 2025. Its knowledge cutoff is June 30, 2025.