All models
QwenText generation
Qwen3.8 Omni Flash
qwen/qwen3.8-omni-flash−41%Qwen3.8 Omni Flash. Accepts text and image input.
Quick Start
API previewimport OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cheapllm.wtf/v1",
apiKey: "wtf_...",
});
const response = await client.chat.completions.create({
model: "qwen/qwen3.8-omni-flash",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Hello!" },
],
});
console.log(response.choices[0].message.content);Use your API key to authenticate requests.
Hello! How can I help you today?
Example response · no request has been sent
API Details
Chat CompletionsChat Completions
Request
model stringRequired · The model ID to use for the request.messages arrayRequired · Conversation messages with a role and content.stream booleanOptional · Receive the response as server-sent events.max_tokens integerOptional · Maximum number of output tokens to generate.temperature numberOptional · Sampling temperature, when supported by the model.Response
choices arrayGenerated choices and token usage.usage objectprompt_tokens · completion_tokens · total_tokens