Questions? hello@viberation.devGet supportBlogDocsChangelog
Get started

Qwen

Alibaba's open-weight family, with a coder model in nearly every size.

Qwen is Alibaba's model family and the largest open-weight line there is — dozens of sizes from a few billion parameters up to the Max models, most of them published so you can run them yourself. For vibe coders the draw is the Qwen Coder models: strong at code for the price, cheap to call through a provider, and small enough at the low end to run on your own machine. The flagship Max models take text, images and video and go up to a million tokens of context.

At a glance — Qwen3 235B A22B Thinking 2507

Cost
$0.23 in · $2.30 out per 1M tokensBudget
Memory
131K tokens — about 200 pages
Reads
Text
Can do
  • Use tools (agents)
  • Structured output
  • Thinking mode
Good at
Coding: better than 23% · Agentic work: better than 19% · Overall: better than 21%
Reliability
99.71% uptime, last 24h
Released
Jul 25, 2025
Advanced details
API model ID
qwen/qwen3-235b-a22b-thinking-2507
Max output
118K tokens
Knowledge cutoff
2025-06-30
Tokenizer
Qwen3
Coding index
22.1
Agentic work index
1.3
Overall index
12.7

Providers

The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.

ProviderInput /1MOutput /1MCached /1MMax outputUptime 24h
Alibaba$0.23$2.30—118K99.71%
Novita · fp8$0.30$3.00—33K82.57%
Venice · fp8$0.45$3.50—16K93.17%

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logprobs
  • max_tokens
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.

Key info

Pricing
Open source
Category
Models
Best for
Intermediate
Made by
Alibaba
Weights
Open, most sizes
Good for
Cheap coding models, and running one yourself

More in Models

  • France's frontier lab, with the small models everyone self-hosts.

    Models
  • Meta's current line, built for long multi-agent runs.

    Models
  • The open-weight family everyone else gets benchmarked against.

    Models
  • Google's open models — Gemini's research, small enough to self-host.

    Models