Model Library
AlibabaReleased April 28, 2025Qwen3 235B
Alibaba · Released April 28, 2025
Intelligence score
11
At a glance
- Intelligence
- 11
- Speed
- 54.9tokens/sec
- Latency
- 2.81stime to first token
- Input price
- $0.70per 1M tokens
- Output price
- $2.80per 1M tokens
- Context window
- 33Ktokens
- Parameters
- 235billions
Summary
Comparison summary
Qwen3 235B A22B (Non-reasoning) scores 11 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17). Qwen3 235B A22B (Non-reasoning) generates output at 54.9 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). Qwen3 235B A22B (Non-reasoning) costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.60) and $2.80 per 1M output tokens (somewhat higher than average, median: $2.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 235B |
|---|---|
| Provider | Alibaba |
| Release date | April 28, 2025 |
| Intelligence score | 11 |
| Speed | 54.9 tokens/sec |
| Latency (TTFT) | 2.81s |
| Input price | $0.70 / 1M tokens |
| Output price | $2.80 / 1M tokens |
| Context window | 33,000 tokens |
| Parameters | 235B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-235b-a22b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 235B, as listed in the catalog record
- Input$0.70
- Output$2.80
| Token type | Price per 1M |
|---|---|
| Input | $0.70 |
| Output | $2.80 |
Model Intelligence legacy profile: qwen3-235b-a22b-instruct
FAQ · 20
Frequently asked questions
Qwen3 235B A22B (Non-reasoning) was released on April 28, 2025.
Qwen3 235B A22B (Non-reasoning) was created by Alibaba.
Qwen3 235B A22B (Non-reasoning) scores 11 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17).
Qwen3 235B A22B (Non-reasoning) generates output at 54.9 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
Qwen3 235B A22B (Non-reasoning) has a time to first token (TTFT) of 2.81s (based on Alibaba's API), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 2.33s).
Qwen3 235B A22B (Non-reasoning) costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.60) and $2.80 per 1M output tokens (somewhat higher than average, median: $2.40), based on Alibaba's API.
Qwen3 235B A22B (Non-reasoning) costs $0.70 per 1M input tokens and $2.80 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.91 per 1M tokens. Pricing may vary by provider.
No, Qwen3 235B A22B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 235B A22B (Non-reasoning) supports text input.
Qwen3 235B A22B (Non-reasoning) supports text output.
No, Qwen3 235B A22B (Non-reasoning) does not support image input. It can only process text.
No, Qwen3 235B A22B (Non-reasoning) is not multimodal. It only supports text input.
Qwen3 235B A22B (Non-reasoning) has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 235B A22B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 235B A22B (Non-reasoning) has 235 billion parameters (22 billion active).
Qwen3 235B A22B (Non-reasoning) is a Mixture of Experts (MoE) model with 235 billion total parameters, but only 22 billion active parameters are used during inference.
Qwen3 235B A22B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 235B A22B (Non-reasoning) achieves a score of 11 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 235B A22B (Non-reasoning) is available via API through 2 providers.
Qwen3 235B A22B (Non-reasoning) is available through 2 API providers.