The Orchestrator › Models › Qwen
Qwen: 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
| Provider | Qwen |
| Model ID | qwen/qwen3.5-122b-a10b |
| Context window | 262K tokens (262,144) |
| Modalities | text + image + video → text |
| Tokenizer | Qwen3 |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2026-02-25 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | qwen/qwen3.5-122b-a10b | $0.26 | $2.08 | 262K |
| standard | TrustedRouter | qwen/qwen3.5-122b-a10b | $0.232 | $2.19 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.232 | $2.19 | 262K |
| 2026-11-14 | $0.26 | $2.08 | 262K |
Capabilities
Vision (image input)Video inputAgentic tool useStructured outputs256K+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p