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 overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.
- Input / output price
- $0.115 / $0.917 per 1M
- Context
- 262K tokens
- Released
- Feb 24, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/qwen3.5-122b-a10b | $0.115/M | $0.917/M |
EmpirioLabs empiriolabs/qwen3.5-122b-a10b | $0.115/M | $0.917/M |
Novita novita/qwen3.5-122b-a10b | $0.40/M | $3.20/M |
Qwen qwen/qwen3.5-122b-a10b | $0.40/M | $3.20/M |
OpenRouter openrouter/qwen3.5-122b-a10b | $0.26/M | $2.08/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.26 per 1M
- Average output
- $2.06 per 1M
- Average cache read
- $0.12 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better74tokens/sacross providers
Response latency
Lower is better3.7sacross providers
Benchmarks
4 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Mystery Game PuzzlesEpoch AI | 17% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1417 Elo · #106 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1360 Elo · #99 of 124 | LMArena | Nov 20, 2026 |
| LMArena VisionLMArena | 1226 Elo · #61 of 91 | LMArena | Nov 19, 2026 |
Apps
Use Qwen3.5 122B A10B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen3.5 122B A10B FAQ
Short answers, built from the data on this page.
Qwen3.5 122B A10B is a model from Qwen, released on Feb 24, 2026. 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 overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.
On the Respan gateway, Qwen3.5 122B A10B costs from $0.115 per 1M input tokens and $0.917 per 1M output tokens on Concentrate and EmpirioLabs, after gateway discounts. Averaged across its 5 providers, it costs $0.26 per 1M input tokens and $2.06 per 1M output tokens.
Qwen3.5 122B A10B is available through 5 providers: Concentrate, EmpirioLabs, Novita, Qwen, and OpenRouter.
Qwen3.5 122B A10B accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen/qwen3.5-122b-a10b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3.5 122B A10B has 4 published benchmark scores, including Mystery Game Puzzles 17% and LMArena Elo 1417. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.