impulse

Qwen3.5 122B A10B

Open weights

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.

API id qwen3.5-122b-a10bReleased 25 Feb 2026 (Feb 2026)
Input / 1M
$0.113
at AIHubMix
Output / 1M
$0.901
at AIHubMix
Context window
262K
tokens
Max output
66K
tokens per reply
Hosts
6
6 listings
Released
Feb 2026
25 Feb 2026

Pricing

List prices at AIHubMix, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.113$0.901

What it costs a month

At AIHubMix list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$101
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$86.48
  • Coding agent1,000 requests a day, 40K in / 2K out$189
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$486
Use your own numbers

Where to run it

6 hosts serve Qwen3.5 122B A10B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
AIHubMixGateway
qwen3.5-122b-a10b
$0.113 / $0.901
qwen3-5-122b-a10b
$0.115 / $0.917
+2% vs headline
qwen3.5-122b-a10b
$0.25 / $1.75
+102% vs headline
DeepInfraInference
Qwen3.5-122B-A10B
$0.29 / $2.40
+164% vs headline
GMI CloudInference
Qwen3.5-122B-A10B
$0.40 / $3.20
+255% vs headline
Novita AIInference
qwen3.5-122b-a10b
$0.40 / $3.20
+255% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Features
Built-in web search
Open weights
License: Apache-2.0
Runs in about 300.2 GB of GPU memory
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than AIHubMix.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    35% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    35% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    15% less

Open-weight picks

  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    15% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    18% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    42% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    48% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedQwen35 122B A10BLatest$0.22 / $2.20
  2. Feb 2026Qwen3.5 122B A10BThis page$0.113 / $0.901

Call it

Using AIHubMix's API.

Python
from litellm import completion

response = completion(
    model="aihubmix/qwen3.5-122b-a10b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3.5 122B A10B cost?

On AIHubMix, Qwen3.5 122B A10B costs $0.113 per million input tokens and $0.901 per million output tokens.

Which APIs offer Qwen3.5 122B A10B?

Qwen3.5 122B A10B runs on 6 APIs: AIHubMix, EmpirioLabs AI, LibertAI, DeepInfra, GMI Cloud and Novita AI.

What is Qwen3.5 122B A10B's context window?

262K tokens, with up to 66K tokens in one reply.

Is Qwen3.5 122B A10B being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Qwen3.5 122B A10B?

Yes. Qwen35 122B A10B is the newest model in this line.

What are cheaper alternatives to Qwen3.5 122B A10B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (35% less), GPT-6 Luna on OpenAI (35% less) and Mistral Small 2603 on Mistral AI (15% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Qwen3.5 122B A10B released?

Alibaba Qwen released it on 25 Feb 2026.

What is Qwen3.5 122B A10B's API model id?

Use qwen3.5-122b-a10b with AIHubMix. Other hosts use their own ids: qwen3-5-122b-a10b on EmpirioLabs AI, Qwen3.5-122B-A10B on DeepInfra, Qwen3.5-122B-A10B on GMI Cloud.

Sources

Raw catalog entry for qwen3.5-122b-a10b on AIHubMix
{
  "input_cost_per_token": 1.126e-7,
  "litellm_provider": "aihubmix",
  "max_input_tokens": 262144,
  "max_output_tokens": 65536,
  "mode": "chat",
  "output_cost_per_token": 9.008e-7,
  "source": "https://aihubmix.com/api/v1/models",
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_vision": true,
  "supports_web_search": true
}