Back to models
Try in Agents
Model · OpenAI
GPT-6 Astra (Ultrafast)
openai/gpt-6-astra-ultrafast
OpenAI's GPT-6 Astra on the Ultrafast service tier, its fastest output (6x price)
reasoningvisioncaching
Specs
Context
1.1M
Max output
128K
Provider
OpenAI
Input
$60.00/ 1M tokens
Output
$300.00/ 1M tokens
Cache read
$6.00/ 1M tokens
Cache write
$75.00/ 1M tokens
Try it
Chat with GPT-6 Astra (Ultrafast)Terramind 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("gpt-6-astra-ultrafast"),
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 OpenAI
| Model | Context | In | Out | Capabilities |
|---|---|---|---|---|
| 128K | $2.50 | $10.00 | visionaudiocaching | |
| 400K | $0.250 | $2.00 | reasoningvisioncaching | |
| 400K | $1.75 | $14.00 | reasoningvisioncaching | |
| 1.1M | $2.50 | $15.00 | reasoningvisioncaching | |
| 1.1M | $30.00 | $180.00 | reasoningvision | |
| 1M | $5.00 | $30.00 | reasoningvisioncaching | |
| 1M | $30.00 | $180.00 | reasoningvision | |
| 1.1M | $4.00 | $20.00 | reasoningvisioncaching |