Qwen3 VL 30B A3B Thinking: API Pricing, Context Window & Benchmarks
Qwen3 VL 30B A3B Thinking is a language model from Qwen, released in September 2025, with multimodal input.
Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video. Built on a 235B-parameter architecture, it integrates early joint training of
Qwen3 VL 30B A3B Thinking benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
How Qwen3 VL 30B A3B Thinking performs across real-world prompt categories.
Performance by conversation depth
How Qwen3 VL 30B A3B Thinking holds up as conversations get longer.
Quality Tracker
Qwen3 VL 30B A3B Thinking Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Aug 24 2026Qwen3 VL 30B A3B Thinking pricing
Providers
Qwen3 VL 30B A3B Thinking starts at $0.200 per million input tokens and $1.00 per million output tokens via Novita. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Novita | $0.200 | — | $1.00 | 131.1K/32.8K | — | — | / |
 DeepInfra | $0.290 | — | $0.990 | 262.1K/262.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Qwen3 VL 30B A3B Thinking model size
Qwen3 VL 30B A3B Thinking has 31 billion parameters. See how it compares to other models in the same parameter range.
Qwen3 VL 30B A3B Thinking context window
Input and output token limits for Qwen3 VL 30B A3B Thinking, plus how it ranks on long-context understanding.
Qwen3 VL 30B A3B Thinking API
Available from the model provider
Qwen3 VL 30B A3B Thinking has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationQwen3 VL 30B A3B Thinking latency
Qwen3 VL 30B A3B Thinking time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Qwen3 VL 30B A3B Thinking examples
Recent arena outputs from Qwen3 VL 30B A3B Thinking, picked from the highest-ranked matchups.
Qwen3 VL 30B A3B Thinking license
Qwen3 VL 30B A3B Thinking is released under the Apache 2.0 license, which permits commercial use, has 31.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 31.0B
Apache License 2.0 - allows commercial use
Qwen3 VL 30B A3B Thinking resources
Official sources for Qwen3 VL 30B A3B Thinking: api documentation, official playground, official launch post, source repository, model weights.
Qwen3 VL 30B A3B Thinking vs other models
The most-compared alternatives to Qwen3 VL 30B A3B Thinking are GPT OSS 20B High, Grok-2, Gemini 2.0 Flash Thinking. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen3 VL 30B A3B Thinking
Models ranked just above and below Qwen3 VL 30B A3B Thinking by LLM Stats score.
FAQ
Common questions about Qwen3 VL 30B A3B Thinking.