Qwen3.5 122B-A10B and Qwen3.5 Flash side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Alibaba Cloud Text GenerationQwen3.5 122B-A10B and Qwen3.5 Flash are both Alibaba Cloud models in the Text Generation category, available through the EmpirioLabs API.
| Spec | Qwen3.5 122B-A10B | Qwen3.5 Flash |
|---|---|---|
| Model ID | qwen3-5-122b-a10b | qwen3-5-flash |
| Author | Alibaba Cloud | Alibaba Cloud |
| Released | Feb 24, 2026 | Feb 24, 2026 |
| Context window | 258K tokens | 995.9K tokens |
| Max output | 64,000 tokens | 32,768 tokens |
| Input | Text Image Video | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Mode | JSON Mode |
| Region | China | Singapore |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/qwen3-5-122b-a10b:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/qwen3-5-flash:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Qwen3.5 122B-A10B | Qwen3.5 Flash |
|---|---|---|
| temperature | 0 to 1.99 Default: 0.7 | 0 to 1.99 Default: 0.7 |
| top_p | 0 to 1 Default: 0.9 | 0 to 1 Default: 0.9 |
| max_tokens | 1 to 64000 | 1 to 65536 |
| stop | string | - |
| enable_thinking | boolean Default: true | boolean Default: true |
| reasoning_effort | none, low, medium, high, max | - |
| thinking_budget | 1 to 81920 | 1 to 81920 |
| seed | 0 to 2147483647 | 0 to 2147483647 |
| top_k | 1 to 100 | 1 to 100 |
| presence_penalty | -2 to 2 | -2 to 2 |
| repetition_penalty | 0.1 to 2 | 0.1 to 2 |
| n | 1 to 4 Default: 1 | 1 to 4 Default: 1 |
| logprobs | boolean Default: false | boolean Default: false |
| top_logprobs | 0 to 5 Default: 0 | 0 to 5 Default: 0 |
| vl_high_resolution_images | boolean Default: true | boolean Default: true |
| max_pixels | 4096 to 16777216 Default: 2621440 | 4096 to 16777216 Default: 2621440 |
Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens.
Built-in tools (billed only when invoked)
Text-to-Image Search and Image-to-Image Search use the Image Search pricing row. Each invoked image search is billed at that listed per-call rate.
Qwen3.5 122B-A10B serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id qwen3-5-122b-a10b. Both models are called through the same endpoint. Set model to qwen3-5-122b-a10b or qwen3-5-flash. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-5-122b-a10b",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Both models were released on Feb 24, 2026. Qwen3.5 Flash has the larger context window: 995.9K tokens, against 258K for Qwen3.5 122B-A10B. Qwen3.5 122B-A10B returns up to 64,000 output tokens per response, Qwen3.5 Flash up to 32,768. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.