Qwen: Qwen3.5-122B-A10B
by QwenQwen: Qwen3.5-122B-A10B is a large language model from Qwen. It costs $0.260 per million input tokens and $2.08 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.260
- Output / 1M tokens
- $2.08
- Cached input / 1M
- -
- Context window
- 262K
Not supported
tokens
Who serves it cheapest
5 hosts serve Qwen3.5-122B-A10B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlowCheapestfp8 | $0.260 | $2.08 | 262K | - | 88.7% |
| Alibaba | $0.260 | $2.08 | 262K | - | 96.4% |
| DeepInfrafp4 | $0.290 | $2.40 | 262K | - | 99.4% |
| AtlasCloudfp8 | $0.300 | $2.40 | 262K | - | 98.0% |
| Novitabf16 | $0.400 | $3.20 | 262K | - | 99.8% |
The spread between SiliconFlow and Novita is 1.5× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 16.2
- Coding index
- 45.7
- Agentic index
- 9.6
About Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Specifications
| Model ID | qwen/qwen3.5-122b-a10b |
|---|---|
| Provider | Qwen |
| Context window | 262K tokens |
| Max output | 66K tokens |
| Input modalities | text, image, video |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - Qwen/Qwen3.5-122B-A10B |
| Released | February 25, 2026 |
Cheaper alternatives
Models that cost less than Qwen3.5-122B-A10B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Qwen: Qwen3.5-122B-A10B cost?
$0.260 per million input tokens and $2.08 per million output tokens.
What is the context window of Qwen: Qwen3.5-122B-A10B?
262K tokens, with up to 66K tokens of output per request.
Which provider serves Qwen: Qwen3.5-122B-A10B cheapest?
SiliconFlow at $0.260 per million input tokens - 1.5× cheaper than Novita, the most expensive of the 5 hosts serving it.
Confirm against the source: Qwen official pricing.