Endpoint coverage
Exposes 1 public endpoint(s): chat_completion.
Dense open-weight Qwen3.6 vision model for agentic coding; 256K context; OpenAI-compatible API
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/qwen3.6-27b:generateContent
POST /v1beta/models/qwen3.6-27b:streamGenerateContent
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.6-27b",
"messages": [
{
"role": "user",
"content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."
}
]
}'
from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="qwen3.6-27b",
messages=[{"role": "user", "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."}]
)
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: "qwen3.6-27b",
messages: [{ role: "user", content: "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it." }]
});
9 versions available
Qwen3.6-27B is a dense native vision-language model from Alibaba Qwen, released with open weights under Apache 2.0 on April 22, 2026. It is built on Qwen3.5-27B. Qwen reports flagship-level agentic coding that surpasses Qwen3.5-397B-A17B, plus stronger STEM reasoning, spatial intelligence, OCR, and video understanding.
It has thinking and non-thinking modes and adds a mechanism Qwen calls Thinking Preservation. The context window is 262,144 tokens, with up to 65,536 output tokens. Alibaba lists function calling and structured outputs as supported.
On RunAPI, call qwen3.6-27b through the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions) with an OpenAI SDK pointed at https://runapi.ai/v1. Images go in image_url parts inside messages[].content[], and tools use the standard OpenAI tools format.
Pick any model and generate in seconds.
| Provider | Alibaba |
| Model ID | qwen3.6-27b |
| Modality | Text |
| Task types | Synchronous |
| API endpoint | /v1/chat/completions |
| /v1/responses |
| /v1/messages | |
| /v1beta/models/qwen3.6-27b:generateContent | |
| /v1beta/models/qwen3.6-27b:streamGenerateContent | |
| Billing unit | 1K tokens |
| Catalog status | Operational |
Sign up for free and create an API key for qwen3.6-27b from the dashboard.
POST to /v1/chat/completions with the qwen3.6-27b model slug and your parameters.
Read the completed qwen3.6-27b response directly from the endpoint.
Exposes 1 public endpoint(s): chat_completion.
Metered by 1K tokens with no subscription requirement.
No request parameters are published for this endpoint.
Answer customer questions from a private knowledge base, reducing ticket volume.
Draft contract summaries and flag key clauses for attorney review.
Auto-generate unit tests, code reviews, and refactoring suggestions in CI.
Verified customer feedback is not available for this model yet.
Qwen reports that the 27B dense model surpasses the Qwen3.5 flagship in agentic coding. Both have a 262,144-token context window and accept images. Compare them on your own coding tasks before you switch.
Qwen3.6-27B is dense, so all 27B parameters run for every token. Qwen3.6-35B-A3B is a Mixture-of-Experts model that activates 3B parameters per token. Qwen positions the 27B model for flagship-level agentic coding.
Qwen3.6-27B is built on Qwen3.5-27B. Qwen reports better agentic coding, STEM reasoning, spatial intelligence, OCR, and video understanding.
Yes. Alibaba lists function calling as supported. Send tools in the OpenAI format on Chat Completions and the model returns tool_calls.
Pass the model ID shown in the quickstart.
Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.
Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.
Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.
Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.
No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.
We're here to help with enterprise setup, integrations, and technical questions.
Contact Us