Back to models
Model · Qwen
Qwen

Qwen 3.8 Max Prime

alibaba/qwen3.8-max-prime
Try in Agents

The high-speed edition of Qwen 3.8 Max — same 2.4T-parameter MoE and capabilities, served faster

reasoningvisioncachingfast
Specs
Context
1M
Max output
128K
Provider
Qwen
Input
$4.00/ 1M tokens
Output
$12.00/ 1M tokens
Cache read
$0.500/ 1M tokens
Try it
Chat with Qwen 3.8 Max PrimeTerramind API
⌘+Enter to run
Code
import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("qwen3.8-max-prime"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by Qwen
ModelContextInOutCapabilities
Qwenalibaba/qwen3-coder131K$1.00$5.00
reasoningcaching
Qwenalibaba/qwen3-coder-flash256K$0.500$1.20
Qwenalibaba/qwen3-coder-next262K$0.500$1.20
Qwenalibaba/qwen3.5-flash1M$0.100$0.400
visioncaching
Qwenalibaba/qwen3.6-plus1M$0.500$3.00
reasoningvisioncaching
Qwenalibaba/qwen3-max262K$1.20$6.00
reasoningvisioncaching
Qwenalibaba/qwen3.8-max1M$2.00$6.00
reasoningvisioncaching
Qwenalibaba/qwen3.8-flash991K$0.150$0.470
reasoningvisioncaching