Back to models
Try in Agents
Model · Qwen
Qwen 3.8 Flash
alibaba/qwen3.8-flash
Qwen's fast, low-cost multimodal model with reasoning and a 1M-token context
reasoningvisioncaching
Specs
Context
991K
Max output
128K
Provider
Qwen
Input
$0.150/ 1M tokens
Output
$0.470/ 1M tokens
Cache read
$0.016/ 1M tokens
Try it
Chat with Qwen 3.8 FlashTerramind 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-flash"),
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
| Model | Context | In | Out | Capabilities |
|---|---|---|---|---|
| 131K | $1.00 | $5.00 | reasoningcaching | |
| 256K | $0.500 | $1.20 | ||
| 262K | $0.500 | $1.20 | ||
| 1M | $0.100 | $0.400 | visioncaching | |
| 1M | $0.500 | $3.00 | reasoningvisioncaching | |
| 262K | $1.20 | $6.00 | reasoningvisioncaching | |
| 1M | $2.00 | $6.00 | reasoningvisioncaching | |
| 1M | $4.00 | $12.00 | reasoningvisioncaching |