OpenAIMultimodal Model

GPT-6 Astra

OpenAI's GPT-6 flagship for the hardest agentic coding and knowledge-work tasks: a 922K-token context with image input, tool calling, structured outputs, and reasoning effort from none up to xhigh. Built for deep multi-step work where quality dominates cost.

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "gpt-6-astra",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "gpt-6-astra",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}

Prompt caching

Keep the prompt prefix byte-identical across calls: same text, same order.
Pass a stable prompt_cache_key string. It is a routing-affinity hint; it does not create or identify cached content.
Check usage.prompt_tokens_details.cached_tokens in the response to confirm cache reads.

{
  "model": "gpt-4o",
  "prompt_cache_key": "v1-stable-prefix",
  "messages": [{ "role": "user", "content": "..." }]
}

{
  "model": "gpt-4o",
  "prompt_cache_key": "v1-stable-prefix",
  "messages": [{ "role": "user", "content": "..." }]
}

Related models

Model

InputCache readOutput

Kimi K3

1024K input contextVisionToolsReasoning$3.00 / $15.00

256K input contextTools$0.102 / $0.48

125K input context$0.05 / $0.23

$0.05

$0.23

Schematron V2 Turbo

125K input context$0.03 / $0.15

$0.03

$0.15

Start building with GPT-6 Astra today

Serverless, OpenAI-compatible, and billed per token. No commitments.