Qwen logo

Qwen3.6 Flash

by Qwen
qwen/qwen3.6-flash
28.5% off

Qwen3.6 Flash is a text and image and video-input model by Qwen, available through the AgentSky API as qwen/qwen3.6-flash at $0.17875 per million input tokens and $1.0725 per million output tokens, with a 1M context window.

A fast multimodal Qwen model.

Pricing

USD per million tokens, using your plan when signed in. Each request uses the tier matching its full input context, including cached input; output tokens do not choose the tier.
Input context (tokens)Cache modeThinkingInputOutputCache readCache write
Up to 256,000NoneStandardOfficial price: $0.25Sale price: $0.17875Official price: $1.50Sale price: $1.0725——
Up to 256,000ExplicitStandardOfficial price: $0.25Sale price: $0.17875Official price: $1.50Sale price: $1.0725Official price: $0.025Sale price: $0.017875Official price: $0.3125Sale price: $0.2234375
256,001–1,000,000NoneStandardOfficial price: $1.00Sale price: $0.715Official price: $4.00Sale price: $2.86——
256,001–1,000,000ExplicitStandardOfficial price: $1.00Sale price: $0.715Official price: $4.00Sale price: $2.86Official price: $0.1Sale price: $0.0715Official price: $1.25Sale price: $0.89375

Every response carries its own cost. Balance and per-call records: /v1/credits and /v1/generation.

Use it

Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "qwen/qwen3.6-flash",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response

Questions