Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • 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
  • AI Site Map

Connect

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

Qwen: Qwen3 32B

qwen/qwen3-32b

Model weights
Compare

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Modalities
In / Out Price
$0.08 / $0.28per 1M
Context
131K
Released
Apr 28, 2025
Knowledge Cutoff
Mar 2025
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

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), or Floor (cheapest).

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.

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.

API

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.08$0.28--0.41s29 tps
98.86%
$0.14$0.40$0.090.59s44 tps
99.96%
$0.14$0.57--1.81s33 tps
97.83%
Throughput
44tok/s

P50, best across providers

Latency
0.41s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchDeepInfra56.7%48.3%Tenstorrent55.1%43.4%
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.
99.75%

Availability over the last 3 days

Last 72 hours
Availability 99.75%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.32%
Without Routing
98.70%

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 provider routing options.

1.
Favicon for https://www.mydreamcompanion.com/
My Dream Companion
new
19.7Btokens
2.
Favicon for https://ariva.group/
pdfparser-resume
new
862Mtokens
3.
Favicon for https://geo.hybrid.co/
GEO Intelligence
new
644Mtokens
4.
Favicon for https://github.com/testbank-ai/golden-ocr
Solve Golden-OCR Judge
new
504Mtokens
5.
Favicon for https://relationbench.local/
RelationBench v5
new
290Mtokens

Frequently asked questions

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation.

Qwen3 32B costs $0.08/M input tokens and $0.28/M output tokens.

Qwen3 32B has a 131,072 token context window. It supports up to 16,384 completion tokens.

Yes. Qwen3 32B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Qwen3 32B is served by 3 providers on OpenRouter: DeepInfra, Tenstorrent, and SiliconFlow. 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 32B was released on April 28, 2025. Its knowledge cutoff is March 31, 2025.