Qwen 3.5 122B
Access Qwen 3.5 122B through one API key. Efficient MoE model.
Alibaba's mid-size MoE model. 122B total parameters with 10B active for efficient inference.
No credit card required. Takes 30 seconds.
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Try it live
Send a message and see Qwen 3.5 122B respond in real time.
Maximum tokens in the response.
Real-time tokens
Context Window
262K tokens
Max Output
66K tokens
Input Price
$0.36 / 1M tokens
Output Price
$2.91 / 1M tokens
Strengths
Qwen 3.5 122B uses a mixture-of-experts design with 122 billion total parameters and 10 billion active per token for efficient mid-size inference.
Activating just 10B of 122B parameters per token keeps latency and cost moderate while retaining strong capability.
Delivers solid reasoning and coding performance, a capable middle tier between the compact and flagship Qwen models.
At $0.36 per 1M input and $2.91 per 1M output tokens, it offers mid-size MoE capability at an accessible price.
Quick start
Copy this snippet and start making calls with Qwen 3.5 122B.
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "qwen/qwen3.5-122b-a10b",
"messages": [
{
"role": "user",
"content": "Explain API gateways in 2 sentences."
}
],
"maxTokens": 256
}),
});
const { data } = await res.json();
console.log(data.message.content);Why use Qwen 3.5 122B through YepAPI?
Qwen 3.5 122B API: efficient mid-size MoE reasoning
Qwen 3.5 122B is Alibaba's mid-size mixture-of-experts model, with 122 billion total parameters and 10 billion active per token. It balances strong reasoning and coding ability with efficient, moderate-cost inference.
Through YepAPI you call Qwen 3.5 122B with one API key on the chat endpoint at $0.36 per 1M input and $2.91 per 1M output tokens, with a 262K context window and 65K output.
What is Qwen 3.5 122B?
Qwen 3.5 122B is a mid-size mixture-of-experts model in Alibaba's Qwen 3.5 family. It has 122 billion total parameters but activates only about 10 billion per token, so it runs at the efficiency of a much smaller model while keeping strong general capability. It handles reasoning, coding, summarization, and writing well, sitting between the compact 35B and flagship 397B variants as a capable middle option. With a 262K-token context window and up to 65,536 tokens of output, it manages large inputs and detailed responses, making it a balanced pick for teams that want solid quality without flagship pricing.
Build with Qwen 3.5 122B via YepAPI
Send chat completion requests to Qwen 3.5 122B over a single YepAPI key on the /v1/ai/chat endpoint — no Alibaba Cloud provisioning. Pass your messages and stream responses; the MoE routing runs server-side. Because one key spans the whole catalog, you can use Qwen 3.5 122B as a balanced default and escalate to 397B for the hardest prompts or drop to 35B for bulk work, all without re-authenticating. It fits naturally into assistants, coding tools, and processing pipelines.
Qwen 3.5 122B API pricing — $0.36/1M input, $2.91/1M output
Qwen 3.5 122B costs $0.36 per 1M input tokens and $2.91 per 1M output tokens on YepAPI. Its MoE efficiency means you pay mid-tier rates for capability close to larger models, making it a cost-effective workhorse for steady production traffic. You pay only for tokens used, with no minimums or seats, and one balance covers it alongside every other model on the platform.
Qwen 3.5 122B for balanced production workloads
Qwen 3.5 122B is a strong default for everyday production: customer-facing assistants, code generation and review, document analysis, and content workflows that need good reasoning without flagship cost. Its 262K context supports large inputs, and its 10B active parameters keep responses fast. When you want dependable quality across a wide range of tasks at a moderate price, it is an effective middle-ground model.
Try Qwen 3.5 122B free
Start with $5 in free credit — no card required. Sign up, grab your API key, and test Qwen 3.5 122B on your typical workload to judge its balance of quality and cost before you spend.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
Alibaba's mid-size MoE model. 122B total parameters with 10B active for efficient inference.
Input tokens cost $0.36 per 1M tokens and output tokens cost $2.91 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.
Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.
Qwen 3.5 122B supports a 262K token context window with up to 66K output tokens per request.
Ready to use Qwen 3.5 122B?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
Qwen3.7 Max
QwenAccess Qwen3.7 Max through one API key. Alibaba's most capable Qwen model.
Qwen 3.6 Plus
QwenAccess Qwen 3.6 Plus through one API key. Powerful reasoning with 1M context at a great price.
Qwen 3 Coder
QwenAccess Qwen 3 Coder through one API key. Coding-specialized model at an ultra-low price.