Qwen3.5-35B-A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Cheapest input
$0.057
$/MTok · models.dev
Cheapest output
$0.459
$/MTok
Context
262K
tokens
Offers
13
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.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen/qwen3.5-35b-a3b | Merge Gateway | $0.057 | $0.459 | $0.0204 | 131K |
| models.devqwen/qwen3.5-35b-a3b | OrcaRouter | $0.057 | $0.459 | $0 | 262K |
| models.devQwen/Qwen3.5-35B-A3B | DeepInfra | $0.14 | $1 | $0.05 | 262K |
| OpenRouterqwen/qwen3.5-35b-a3b | OpenRouter | $0.14 | $1 | $0 | 262K |
| models.devqwen/qwen3.5-35b-a3b | Kilo Gateway | $0.1625 | $1.30 | $0 | 262K |
| models.devQwen/Qwen3.5-35B-A3B | SiliconFlow (China) | $0.23 | $1.86 | $0 | 262K |
| models.devQwen/Qwen3.5-35B-A3B | SiliconFlow | $0.24 | $1.80 | $0 | 262K |
| models.devQwen/Qwen3.5-35B-A3B | Weights & Biases | $0.25 | $1.25 | $0.25 | 262K |
| models.devqwen/qwen3.5-35b-a3b | Mixlayer | $0.25 | $1.30 | $0 | 262K |
| models.devQwen/Qwen3.5-35B-A3B | Hugging Face | $0.25 | $2 | $0 | 262K |
| models.devqwen/qwen3.5-35b-a3b | Novita AI | $0.25 | $2 | $0 | 262K |
| LiteLLMopenrouter/qwen/qwen3.5-35b-a3b | — | $0.25 | $2 | $0.025 | — |
| LiteLLMqwen/qwen3.5-35b-a3b | — | $0.25 | $2 | $0.025 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- In: audio
- Out: text
Knowledge cutoff: 2025-01Released: 2026-02-01Family: 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.
Sources: Arena AI, Artificial Analysis. See /benchmarks.