Skip to content
  • Models
  • Rankings
  • Ori
ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • 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
  • AI Site Map

Connect

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

Qwen: Qwen3.5-27B

qwen/qwen3.5-27b

Model weights
Compare

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.

Modalities
In / Out Price
$0.195 / $1.56per 1M
Context
262K
Released
Feb 25, 2026
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 and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen: Qwen3.5-27B (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen3.5 27B (Reasoning) Intelligence Index22.9
Artificial AnalysisQwen3.5 27B (Reasoning) GPQA Diamond85.8%
Artificial AnalysisQwen3.5 27B (Reasoning) HLE23.9%
Artificial AnalysisQwen3.5 27B (Reasoning) IFBench75.6%
Artificial AnalysisQwen3.5 27B (Reasoning) τ²-Bench Telecom93.9%
Artificial AnalysisQwen3.5 27B (Reasoning) AA-LCR77.7%
Artificial AnalysisQwen3.5 27B (Reasoning) CritPt0.9%
Artificial AnalysisQwen3.5 27B (Reasoning) Terminal-Bench Hard32.6%
Artificial AnalysisQwen3.5 27B (Reasoning) AA-Omniscience Accuracy20.7%
Artificial AnalysisQwen3.5 27B (Reasoning) AA-Omniscience Non-Hallucination Rate18.5%
Artificial AnalysisQwen3.5 27B (Non-reasoning) Intelligence Index19.4
Artificial AnalysisQwen3.5 27B (Non-reasoning) GPQA Diamond84.2%
Artificial AnalysisQwen3.5 27B (Non-reasoning) HLE13.9%
Artificial AnalysisQwen3.5 27B (Non-reasoning) IFBench46.9%
Artificial AnalysisQwen3.5 27B (Non-reasoning) τ²-Bench Telecom87.1%
Artificial AnalysisQwen3.5 27B (Non-reasoning) AA-LCR64.0%
Artificial AnalysisQwen3.5 27B (Non-reasoning) CritPt0.3%
Artificial AnalysisQwen3.5 27B (Non-reasoning) Terminal-Bench Hard31.8%
Artificial AnalysisQwen3.5 27B (Non-reasoning) AA-Omniscience Accuracy15.7%
Artificial AnalysisQwen3.5 27B (Non-reasoning) AA-Omniscience Non-Hallucination Rate24.9%

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.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$0.195$1.56--4.08s18 tps
97.23%
$0.250$2.00--2.67s15 tps
88.11%
$0.260$2.60--1.57s46 tps
100.00%
$0.270$2.16$0.275.03s20 tps
99.92%
$0.300$2.40$0.032.28s24 tps
97.54%
$0.300$2.40--4.02s21 tps
100.00%
Throughput
46tok/s

P50, best across providers

Latency
1.57s

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.
99.67%

Availability over the last 3 days

Last 72 hours
Availability 99.67%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.89%
Without Routing
96.93%

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://docs.all-hands.dev/
OpenHands
AI coding agent that can run commands, browse the web, call APIs
1.02Btokens
2.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
761Mtokens
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.
333Mtokens
4.
Favicon for https://docs.langchain.com/
LangChain
new
262Mtokens
5.
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.
243Mtokens

Frequently asked questions

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.

Qwen3.5-27B costs $0.195/M input tokens and $1.56/M output tokens.

Qwen3.5-27B has a 262,144 token context window. It supports up to 65,536 completion tokens.

Yes. Qwen3.5-27B accepts tools and tool_choice for function calling on 5 of the 6 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Qwen3.5-27B accepts text, images, and video as input and returns text.

Qwen3.5-27B is served by 6 providers on OpenRouter: Alibaba Cloud Int., SiliconFlow, DeepInfra, AtlasCloud, Phala, and NovitaAI. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3.5-27B was released on February 25, 2026.