GPT-5.4 (Azure GPT)
GPT-5.4 (Azure GPT) is a text and image-input model by OpenAI, available through the AgentSky API as openai/gpt-5.4-azure at $1.75 per million input tokens and $10.50 per million output tokens, with a 1.1M context window.
Dedicated Azure GPT resource. This resource uses an independent supplier route and does not fall back to other resources.
Get an API key
Send a request
curl https://gateway.agentsky.dev/v1/chat/completions \ -H "authorization: Bearer $AGENTSKY_API_KEY" \ -H "content-type: application/json" \ -d '{"model":"openai/gpt-5.4-azure","messages":[{"role":"user","content":"In one sentence, what can you help me with?"}],"max_tokens":128}'Run it here, no terminal needed
Or hand it to your agent
Use GPT-5.4 (Azure GPT) through AgentSky. Model id: openai/gpt-5.4-azure OpenAI-compatible base URL: https://gateway.agentsky.dev/v1 · Anthropic base URL: https://gateway.agentsky.dev Docs: https://agentsky.dev/models/openai/gpt-5.4-azure.md Key: <your AgentSky API key>
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 mode | Thinking | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|---|
| Up to 272,000 | Automatic | Standard | — | |||
| 272,001–1,050,000 | Automatic | Standard | — |
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: "openai/gpt-5.4-azure",
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response