Qwen3.5-122B-A10B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Cheapest input
$0.115
$/MTok · models.dev
Cheapest output
$0.917
$/MTok
Context
262K
tokens
Offers
14
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 offers.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen/qwen3.5-122b-a10b | Merge Gateway | $0.115 | $0.917 | $0.023 | 131K |
| models.devqwen/qwen3.5-122b-a10b | OrcaRouter | $0.115 | $0.917 | $0 | 262K |
| models.devqwen/qwen3.5-122b-a10b | Kilo Gateway | $0.26 | $2.08 | $0 | 262K |
| OpenRouterqwen/qwen3.5-122b-a10b | OpenRouter | $0.26 | $2.08 | $0 | 262K |
| models.devQwen/Qwen3.5-122B-A10B | SiliconFlow | $0.26 | $2.08 | $0 | 262K |
| models.devQwen/Qwen3.5-122B-A10B | SiliconFlow (China) | $0.29 | $2.32 | $0 | 262K |
| models.devQwen/Qwen3.5-122B-A10B | DeepInfra | $0.29 | $2.40 | $0 | 262K |
| models.devQwen/Qwen3.5-122B-A10B | Hugging Face | $0.4 | $3.20 | $0 | 262K |
| models.devqwen/qwen3.5-122b-a10b | Mixlayer | $0.4 | $3.20 | $0 | 262K |
| models.devQwen/Qwen3.5-122B-A10B | NEAR AI Cloud | $0.4 | $3.20 | $0 | 131K |
| models.devqwen/qwen3.5-122b-a10b | Novita AI | $0.4 | $3.20 | $0 | 262K |
| LiteLLMopenrouter/qwen/qwen3.5-122b-a10b | — | $0.4 | $2 | $0.04 | — |
| LiteLLMqwen/qwen3.5-122b-a10b | — | $0.4 | $2 | $0.04 | — |
| models.devqwen/qwen3.5-122b-a10b | TensorX | $0.5 | $3.50 | $0.125 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- In: audio
- Out: text
Knowledge cutoff: 2025-04Released: 2026-02-23Family: qwen
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence32.3
- AA coding45.7
- AA agentic20.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.