Qwen3 235B-A22B
Summary
Qwen3 235B-A22B is an open-weight language model from Alibaba (Qwen), released on Apr 2025. It accepts text and generates text, with a 131K-token context window and up to 16K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.20 per million input tokens and $0.80 per million output tokens (Hugging Face Inference Providers), across 1 provider we track. It is scheduled for retirement on 9 Oct 2026.
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | Apr 2025 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 235B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 16K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Retirement date | 9 Oct 2026 [OpenRouter] |
| Hugging Face | Qwen/Qwen3-235B-A22B [Hugging Face] |
Qwen3 235B-A22B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Hugging Face Inference Providers Qwen/Qwen3-235B-A22B | $0.20 | $0.80 | – | 41K | models.dev, 18 Nov 2026 |
Running Qwen3 235B-A22B locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 143 GB | 145 GB | 150 GB |
| Q8_0 (8-bit) | 250 GB | 252 GB | 257 GB |
| FP16 / BF16 (16-bit) | 470 GB | 473 GB | 477 GB |
At 4-bit with an 8K conversation, Qwen3 235B-A22B needs about 145 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3 235B-A22B?
Qwen3 235B-A22B has a context window of 131,072 tokens (131K) and can generate up to 16,384 tokens in a single response, according to models.dev.
How much does the Qwen3 235B-A22B API cost?
Qwen3 235B-A22B is listed from $0.20 per million input tokens and $0.80 per million output tokens (Hugging Face Inference Providers). Prices last verified 18 Nov 2026.
Is Qwen3 235B-A22B open source?
Qwen3 235B-A22B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-235B-A22B under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3 235B-A22B released?
Alibaba (Qwen) released Qwen3 235B-A22B on Apr 2025, according to models.dev.
How much VRAM does Qwen3 235B-A22B need?
About 145 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 252 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | 5 Apr 2025 | 128K | $0.24 | $0.85 | Open |
| DeepSeek V3 0324 | DeepSeek | 24 Mar 2025 | 164K | $0.25 | $1 | Open |
| Uncensored | Cognitivecomputations | 9 Jul 2025 | 128K | $0.20 | $0.90 | Open |
| GLM-4.5-Air | Zhipu AI (Z.ai) | 28 Jul 2025 | 131K | $0.13 | $0.85 | Open |
| Llama-4-Scout-17B-16E-Instruct-FP8 | Meta | 5 Apr 2025 | 128K | $0.10 | $0.30 | Open |
| Mistral Small 3.1 24B | Mistral AI | 17 Mar 2025 | 128K | $0.10 | $0.30 | Open |
Change history
- Status changed from active to deprecated
- No longer listed on alibaba
- No longer listed on openrouter