Alibaba has launched a newer model, Qwen3.5 397B A17B, we suggest considering this model instead.
For more information, see Comparison of Qwen3.5 397B A17B to other models and API provider benchmarks for Qwen3.5 397B A17B.
Qwen3 235B A22B 2507 Instruct Intelligence, Performance & Price Analysis
Model summary
IntelligenceUpdated
Speed
Input Price
Output Price
Verbosity
Qwen3 235B A22B 2507 Instruct is above average in intelligence, but particularly expensive when comparing to other open weight non-reasoning models of similar size. The model supports text input, outputs text, and has a 256k tokens context window.
Qwen3 235B A22B 2507 Instruct scores 18 on the Artificial Analysis Intelligence Index, placing it above average among comparable models (averaging 17).
Pricing for Qwen3 235B A22B 2507 Instruct is $0.70 per 1M input tokens (somewhat expensive, average: $0.50) and $2.80 per 1M output tokens (somewhat expensive, average: $1.50).
At 59 tokens per second, Qwen3 235B A22B 2507 Instruct is slower than average (59).
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 256k ~384 A4 pages of size 12 Arial font |
| Total parameters | 235B |
| Active parameters | 22B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Highlights
IntelligenceUpdated
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Openness
Artificial Analysis Openness Index: Score
Intelligence Index Comparisons
Intelligence vs. Cost per Intelligence Index Task
Price and Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Speed
Measured by Output Speed (tokens per second)
Output Speed
Time per Intelligence Index Task
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about Qwen3 235B A22B 2507 Instruct
Qwen3 235B A22B 2507 Instruct was released on July 21, 2025.
Qwen3 235B A22B 2507 Instruct was created by Alibaba.
Qwen3 235B A22B 2507 Instruct scores 18 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 17).
Qwen3 235B A22B 2507 Instruct generates output at 59.1 tokens per second (based on Alibaba's API), which is above average compared to other open weight non-reasoning models of similar size (median: 59.1 t/s).
Qwen3 235B A22B 2507 Instruct has a time to first token (TTFT) of 2.32s (based on Alibaba's API), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 2.25s).
Qwen3 235B A22B 2507 Instruct 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: $2.50), based on Alibaba's API.
Qwen3 235B A22B 2507 Instruct 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. Compare provider pricing
No, Qwen3 235B A22B 2507 Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 235B A22B 2507 Instruct supports text input.
Qwen3 235B A22B 2507 Instruct supports text output.
No, Qwen3 235B A22B 2507 Instruct does not support image input. It can only process text.
No, Qwen3 235B A22B 2507 Instruct is not multimodal. It only supports text input.
Qwen3 235B A22B 2507 Instruct has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 235B A22B 2507 Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 235B A22B 2507 Instruct has 235 billion parameters (22 billion active).
Qwen3 235B A22B 2507 Instruct 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 2507 Instruct is released under the Apache 2.0 license. This license allows commercial use. View license
Qwen3 235B A22B 2507 Instruct achieves a score of 18 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Qwen3 235B A22B 2507 Instruct is an open weights model that can be self-hosted. View providers
Qwen3 235B A22B 2507 Instruct is an open weights model that can be downloaded and self-hosted. Compare providers