Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

  • About
  • Blog
  • Customers
  • 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: Qwen3.7 Plus

qwen/qwen3.7-plus

Compare

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.

Modalities
In / out price
$0.32 / $1.28per 1M
Context
1.0M
Released
Jun 3, 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 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.

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: Qwen3.7 Plus (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisQwen3.7 Plus Coding Index55.9
Artificial AnalysisQwen3.7 Plus Agentic Index17.5
Artificial AnalysisQwen3.7 Plus GPQA Diamond90.0%
Artificial AnalysisQwen3.7 Plus HLE35.6%
Artificial AnalysisQwen3.7 Plus IFBench78.0%
Artificial AnalysisQwen3.7 Plus τ²-Bench Telecom93.0%
Artificial AnalysisQwen3.7 Plus AA-LCR73.0%
Artificial AnalysisQwen3.7 Plus τ-Bench Banking17.5%
Artificial AnalysisQwen3.7 Plus GDPval-AA13.7%
Artificial AnalysisQwen3.7 Plus CritPt9.1%
Artificial AnalysisQwen3.7 Plus SciCode46.1%
Artificial AnalysisQwen3.7 Plus Terminal-Bench Hard47.0%
Artificial AnalysisQwen3.7 Plus Terminal-Bench 4.01.0%
Artificial AnalysisQwen3.7 Plus Terminal-Bench 2.161.0%
Design ArenaQwen3.7 Plus Models Arena 3D Elo1236
Design ArenaQwen3.7 Plus Models Arena Asciiart Elo1138
Design ArenaQwen3.7 Plus Models Arena Code Categories Elo1267
Design ArenaQwen3.7 Plus Models Arena Data Visualization Elo1276
Design ArenaQwen3.7 Plus Models Arena Game Development Elo1262
Design ArenaQwen3.7 Plus Models Arena SVG Elo1207
Design ArenaQwen3.7 Plus Models Arena UI Component Elo1258
Design ArenaQwen3.7 Plus Models Arena Website Elo1267
Vals AIQwen 3.7 Plus Code Migration12.9%
Vals AIQwen 3.7 Plus EMB49.3%
Vals AIQwen 3.7 Plus Finance Agent (v2)38.2%
Vals AIQwen 3.7 Plus Harvey's Legal Agent Benchmark v10.0%
Vals AIQwen 3.7 Plus Legal Research Bench16.3%
Vals AIQwen 3.7 Plus MortgageTax66.2%
Vals AIQwen 3.7 Plus SAGE89.1%
Vals AIQwen 3.7 Plus SkillsBench54.3%
Vals AIQwen 3.7 Plus Tax Agent Bench10.5%
Vals AIQwen 3.7 Plus Terminal-Bench 2.152.8%
Vals AIQwen 3.7 Plus Vals Index38.6%
Vals AIQwen 3.7 Plus Vals Multimodal Index53.9%
Vals AIQwen 3.7 Plus Vibe Code Bench v1.146.4%

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 Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.32$1.28$0.064$0.40$0.0321.30s51 tok/s
100.00%
$0.32$1.28$0.064$0.40$0.0321.32s50 tok/s
100.00%
ProviderInput / Output /M
ThroughputUptime
  • Favicon for Alibaba
    Input $0.32 / Output $1.28
    Throughput 51 tok/sUptime 100.00%
  • Favicon for Alibaba
    Input $0.32 / Output $1.28
    Throughput 50 tok/sUptime 100.00%
Throughput
51tok/s

P50, best across providers

Latency
1.30s

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.
99.70%

Availability over the last 3 days

Last 72 hours
Availability 99.70%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.73%

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.dxap.ai/
DXAP - Agentic Trading Protocol
new
56.7Btokens
2.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
19.5Btokens
3.
Favicon for https://postlimit.buckydrop.ai/
postlimit-buckydrop.ai
new
11.9Btokens
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.
11.5Btokens
5.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
8.02Btokens
Rest of OpenRouter
4.92B
Top 5 Apps
3.36B

Frequently asked questions

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows.

Qwen3.7 Plus costs $0.32/M input tokens and $1.28/M output tokens, with separate rates for Cache Read at $0.064/M tokens, Cache Creation (5min) at $0.40/M tokens, and Cache Read (5min) at $0.032/M tokens.

Qwen3.7 Plus has a 1,000,000 token context window. It supports up to 131,072 completion tokens.

Yes. Qwen3.7 Plus accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Qwen3.7 Plus accepts text and images as input and returns text.

Qwen3.8 Max Prime, Qwen3.8 Omni Flash, Qwen3.8 Max (0902) and 37 more are other text models from Qwen.

Qwen3.7 Plus was released on June 3, 2026.