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: Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

Model weights
Compare

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.

Modalities

In / Out Price

$0.39 / $2.34per 1M

Context

262K

Released

Feb 16, 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), 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.

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 Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$0.39$2.34--1.42s44 tps
100.00%
$0.45$3.00$0.220.64s49 tps
99.48%
$0.50$3.60$0.300.78s46 tps
97.72%
$0.55$3.50$0.1110.93s15 tps
98.12%
$0.55$3.50$0.551.24s6 tps
99.38%
$0.55$3.50$0.2251.53s34 tps
98.58%
$0.60$3.60--1.77s42 tps
100.00%
$0.60$3.60------
0.00%
$0.60$3.60$0.122.50s42 tps
98.96%
$0.75$4.50--1.60s35 tps
96.71%

Throughput

49tok/s

P50, best across providers

Latency

0.64s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
StreamLake
87.2%--
DeepInfra
87.2%--
NovitaAI
85.5%--
Phala
87.8%77.2%
Alibaba Cloud Int.
86.7%77.2%
+6 more providers
Uptime (3d)

100.00%

Availability (3d)

97.46%

Availability over the last 3 days

Last 72 hours
Availability 97.46%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.80%
Without Routing
90.44%

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://bitsec.ai/
Bitsec
new
3.82Btokens
2.
Favicon for https://portkey.ai/
Portkey AI
Control panel for AI apps
1.87Btokens
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.
886Mtokens
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.
784Mtokens
5.
Favicon for https://perplexity.ai/
Perplexity AI
new
543Mtokens

Frequently asked questions

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Qwen3.5 397B A17B costs $0.39/M input tokens and $2.34/M output tokens.

Qwen3.5 397B A17B has a 262,144 token context window. It supports up to 65,536 completion tokens.

Yes. Qwen3.5 397B A17B accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

Qwen3.5 397B A17B accepts text, images and video as input and returns text.

Qwen3.5 397B A17B is served by 10 providers on OpenRouter: Alibaba Cloud Int., DeepInfra, Parasail, DigitalOcean, AtlasCloud, Phala, NovitaAI, GMICloud and 2 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.

Qwen3.5 397B A17B was released on February 16, 2026.