Qwen API
Alibaba Qwen API access via RunAPI — Apache-2.0 ultra-sparse MoE with 262K context, 80B total / 3.9B active.
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-next-80b-a3b-instruct",
"messages": [
{
"role": "user",
"content": "Analyze this large codebase, identify where request timeouts are handled, and add consistent retry logic across the services."
}
]
}'
from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="qwen3-next-80b-a3b-instruct",
messages=[{"role": "user", "content": "Analyze this large codebase, identify where request timeouts are handled, and add consistent retry logic across the services."}]
)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "qwen3-next-80b-a3b-instruct",
messages: [{ role: "user", content: "Analyze this large codebase, identify where request timeouts are handled, and add consistent retry logic across the services." }]
});
Qwen is Alibaba's Apache-2.0 family of language models. qwen3-next-80b-a3b-instruct uses a hybrid attention architecture (DeltaNet linear + GQA) with an ultra-sparse MoE — 80B total parameters, only ~3.9B active per token across 512 experts. It delivers 262K native context (extendable to 1M) and matches Qwen3-235B-A22B on coding and conversational benchmarks while using 7× fewer active parameters and 10× higher throughput. Available through RunAPI with one key and per-token billing.
- Multiple variants for different speed / quality tiers
- Model skill includes docs, schemas, and setup notes
- Works with app-focused coding workflows
- Failed generations are not charged
Pricing
Technical details
| Model ID | qwen3-next-80b-a3b-instruct |
| Provider | Alibaba |
| Modality | text |
| Task type | synchronous |
| Billing unit | 1K tokens |
| API endpoint | /v1/chat/completions |
| Commercial license | Yes — included via API |
| Status | Operational |
Qwen API endpoints
Use the OpenAI or Anthropic SDK with your RunAPI key. No extra SDK required.
| Endpoint | Protocol |
|---|---|
| /v1/chat/completions | OpenAI compatible |
From model skill to first result in four steps
Choose a model
Pick the model and variant that match your output type, quality bar, and latency target.
Configure
Set your RunAPI key and install the model skill in your coding workspace.
Call
Use the skill instructions to add the model feature inside your application.
Receive
Poll by task ID, stream when supported, or handle the webhook callback.
What is the Qwen API?
Qwen models from Alibaba are Apache-2.0 ultra-sparse MoE LLMs with 262K native context. qwen3-next-80b-a3b-instruct matches models with 7× more active parameters on LiveCodeBench while running at 10× throughput. Through RunAPI they share a single API key with pay-as-you-go token billing, callable from the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages surfaces. These are Qwen text models, distinct from the Qwen 2 image line.
Why route the Qwen API through RunAPI
One auth, every provider
A single RunAPI key unlocks the whole catalog. No separate accounts, no key rotation per integration.
Unified pricing & billing
Per-call pricing in USD, billed monthly. Failed generations are not charged.
Schema-first SDK
Typed schemas and setup notes are packaged in the model skill so implementation starts from the right contract.
Common questions
Which variant should I start with?
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.
Is there a free tier?
New accounts get free first calls on every model. After that, pay per call.
Do you stream results?
Where streaming is available, RunAPI streams end-to-end.
How are failures billed?
Failed generations are not charged.
Are outputs cached?
Generated outputs are stored and retrievable by task ID. Inputs are not cached.
Can I use commercially?
Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.
What about rate limits?
Per-key rate limits scale with usage tier. See pricing page for current limits.
Where can I report issues?
Open an issue on the public GitHub repo or email support.
If you like the Qwen API, try these
Start building with the Qwen API.
- chat_completion