Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

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

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

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

Qwen: Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507

Model weights
Compare

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.

Compared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.

Modalities

In / Out Price

$0.20 / $2.40per 1M

Context

82K

Released

Aug 28, 2025

Knowledge Cutoff

Jun 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQ

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

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.

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.

About Qwen: Qwen3 30B A3B Thinking 2507

OpenRouter makes Qwen: Qwen3 30B A3B Thinking 2507 available through a unified, OpenAI-compatible API using the model ID qwen/qwen3-30b-a3b-thinking-2507. It is served by Alibaba Cloud Int..

Qwen: Qwen3 30B A3B Thinking 2507 accepts text and returns text. It has a 81,920-token context window and a maximum output of 32,768 tokens.

On OpenRouter, Qwen: Qwen3 30B A3B Thinking 2507 costs $0.20/M input tokens and $2.40/M output tokens. It was released on August 28, 2025; its knowledge cutoff is June 30, 2025.

More models from Qwen

  • Qwen3.8 27B
  • Qwen3 Reranker 8B
  • Qwen3 ASR 1.7B

Frequently asked questions

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.

Qwen3 30B A3B Thinking 2507 costs $0.20/M input tokens and $2.40/M output tokens.

Qwen3 30B A3B Thinking 2507 has a 81,920 token context window. It supports up to 32,768 completion tokens.

Yes. Qwen3 30B A3B Thinking 2507 accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

Qwen3.8 27B, Qwen3.8 2.4T A95B, Qwen3.8 Max and 46 more are other text models from Qwen.

Qwen3 30B A3B Thinking 2507 was released on August 28, 2025. Its knowledge cutoff is June 30, 2025.

$0.20$2.400.35s135 tps
100.00%

Throughput

135tok/s

P50, best across providers

Latency

0.35s

P50, best provider

Uptime (3d)

100.00%

Availability (3d)

98.39%

Availability over the last 3 days

Last 72 hours
Availability 98.39%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
96.64%

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/Metta-AI/coworld-heartleaf
heartleaf-selfplay
new
18.7Mtokens
2.
Favicon for https://openwebui.com/
Open WebUI
Open WebUI is a self-hosted AI platform providing a chat interface for Large Language Models.
15.9Mtokens
3.
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.
14.8Mtokens
4.
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.
5.38Mtokens
5.
Favicon for https://github.com/reasonops/faithfulness-pilot
ReasonOps faithfulness pilot
new
4.9Mtokens