Qwen3 235B A22B: API Pricing, Context Window & Benchmarks
Qwen3 235B A22B is a language model from Qwen, released in April 2025.
Qwen3 235B A22B is a large language model developed by Alibaba, featuring a Mixture-of-Experts (MoE) architecture with 235 billion total parameters and 22 billion activated parameters. It achieves competitive results in benchmark
Qwen3 235B A22B benchmarks
Rankings
Quality Tracker
Qwen3 235B A22B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Jul 21 2026Qwen3 235B A22B pricing
Providers
Qwen3 235B A22B starts at $0.100 per million input tokens and $0.100 per million output tokens via Fireworks. See all 4 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Fireworks | $0.100 | $0.100 | 128.0K/128.0K | —/0.78 | 68/— | — | / |
 DeepInfra | $0.200 | $0.600 | 128.0K/128.0K | —/1.23 | 22/— | — | / |
 Novita | $0.200 | $0.800 | 128.0K/128.0K | —/1.02 | 39/— | — | / |
 Together | $0.200 | $0.600 | 128.0K/128.0K | —/0.79 | 24/— | — | / |
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. Success is calculated from completed versus failed requests over the trailing seven days.
Qwen3 235B A22B model size
Qwen3 235B A22B has 235 billion parameters and was trained on 36 trillion tokens. See how it compares to other models in the same parameter range.
Qwen3 235B A22B context window
Input and output token limits for Qwen3 235B A22B, plus how it ranks on long-context understanding.
Qwen3 235B A22B API
Available from the model provider
Qwen3 235B A22B has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationQwen3 235B A22B latency
Qwen3 235B A22B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Qwen3 235B A22B examples
Recent arena outputs from Qwen3 235B A22B, picked from the highest-ranked matchups.
Qwen3 235B A22B license
Qwen3 235B A22B is released under the Apache 2.0 license, which permits commercial use, has 235.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 235.0B
Apache License 2.0 - allows commercial use
Qwen3 235B A22B resources
Official sources for Qwen3 235B A22B: api documentation, official playground, source repository, model weights.
Qwen3 235B A22B vs other models
The most-compared alternatives to Qwen3 235B A22B are Claude 3 Opus, MiMo-V2.5-Pro, GPT-4 Turbo. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen3 235B A22B
Models ranked just above and below Qwen3 235B A22B by LLM Stats score.
FAQ
Common questions about Qwen3 235B A22B.