What is GPT 5.6 Terra built for?

Everyday production work. OpenAI designed GPT 5.6 Terra to balance intelligence and cost, which puts it between the GPT-5.6 Sol flagship and the low-cost GPT-5.6 Luna tier.

How does GPT 5.6 Terra compare with the previous generation?

Performance compares to the previous generation at a lower price, and GPT 5.6 Terra handles agentic coding, biology, and cybersecurity work better. It also reaches answers in fewer tokens.

What context window and output limit does GPT 5.6 Terra support?

1.1M tokens, with up to 128K tokens of output per request, matching the rest of the GPT-5.6 family.

What inputs does GPT 5.6 Terra accept?

Text and images, with text output. Audio and video input are not supported, so route voice work to the gpt-realtime family instead.

When should I escalate from GPT 5.6 Terra to GPT-5.6 Sol?

Escalate when the balanced tier misses on your hardest prompts. Log the turns where GPT 5.6 Terra falls short, retry those against GPT-5.6 Sol, and route only that traffic to the flagship.

What does GPT 5.6 Terra cost?

List pricing is $2 per million input tokens and $12 per million output tokens, with cached input at $0.2. Short-context and long-context requests are priced separately, and AI Gateway mirrors provider pricing with no markup.

Does GPT 5.6 Terra support zero data retention through AI Gateway?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

What are typical latency characteristics?

This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

OpenAI

GPT 5.6 Terra

GPT 5.6 Terra is the balanced model of the GPT-5.6 family, built for everyday production work with performance comparable to the previous generation at a lower price, stronger agentic coding, biology, and cybersecurity results, and a context window of 1.1M tokens.

View API reference

Input and output price: Prices from: Input $2, Output $12, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'openai/gpt-5.6-terra',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out GPT 5.6 Terra by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

GPT 5.6 Terra

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

OpenAI

Legal:Terms•Privacy

1.1M

128K

2.3 s

47 tps

$2/M+4 more

$12/M+4 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

Azure

Legal:Terms•Privacy

1.1M

128K

2.8 s

89 tps

$2/M+1 more

$12/M+1 more

Read$0.20/M

Write$2.50/M

$14/K

07/09/2026

Bedrock

Legal:Terms•Privacy

1.1M

128K

3.8 s

60 tps

$2/M+2 more

$12/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

Getting started

Call GPT 5.6 Terra through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same GPT 5.6 Terra request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `openai/gpt-5.6-terra`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. GPT 5.6 Terra supports up to `128,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 1.1M-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK openai provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['openai', 'azure'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Fast mode

GPT 5.6 Terra can run in fast mode for lower latency by appending -fast to the model ID.

fast-mode.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-terra-fast',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by OpenAI

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

openai/gpt-6-astra

1.1M

3.7 s

47 tps

$10/M+2 more

$50/M+2 more

Read$1/M

Write$12.50/M

$10/K

09/04/2026

openai/gpt-5.6-luna

1.1M

2.4 s

146 tps

$0.20/M+2 more

$1.20/M+2 more

Read$0.02/M

Write$0.25/M

$10/K

07/09/2026

openai/gpt-5.6-sol

1.1M

2.0 s

92 tps

$2/M+2 more

$10/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.4

1.1M

0.9 s

91 tps

$2.50/M+2 more

$15/M+2 more

Read$0.25/M

$10/K

03/05/2026

openai/gpt-5-nano

400K

5.4 s

162 tps

$0.05/M

$0.40/M

Read$0.005/M

$14/K

08/07/2025

openai/text-embedding-3-small

—

$0.02/M

—

01/25/2024

Copy link to headingAbout GPT 5.6 Terra

GPT 5.6 Terra became available on AI Gateway on July 9, 2026 as the balanced model of the GPT-5.6 family, alongside GPT-5.6 Sol and GPT-5.6 Luna. All three GPT-5.6 models handle agentic work across coding, biology, and cybersecurity better than the previous generation, and all three use fewer tokens to reach an answer.

OpenAI describes GPT 5.6 Terra as the GPT-5.6 model that balances intelligence and cost, and it maps to the mini tier of earlier GPT-5 families. Performance compares to the previous generation at a lower price, so GPT 5.6 Terra is a practical default for everyday production traffic: application features, internal tooling, support automation, and the routine steps of a longer agent run.

GPT 5.6 Terra accepts text and image input and returns text, with a context window of 1.1M tokens and up to 128K tokens of output per request. Reasoning tokens, streaming, function calling, and structured outputs are supported, and the Responses API adds web search, file search, code interpreter, computer use, and MCP (Model Context Protocol) tools.

Set the model to openai/gpt-5.6-terra in the AI SDK, the Chat Completions API, the Responses API, or another supported API format, from TypeScript or Python. AI Gateway routing rules can rewrite an existing model slug to openai/gpt-5.6-terra when you want to move traffic without touching application code. List pricing is $2 per million input tokens and $12 per million output tokens, with cached input at $0.2. Upstream list prices came down after launch, and AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: GPT 5.6 Terra corresponds to the mini tier of earlier GPT-5 families, and OpenAI designed it for workloads that balance intelligence and cost. Performance compares to the previous generation at a lower price, which makes GPT 5.6 Terra a straightforward swap for teams already running a mid-tier GPT-5.x model in production.
Configuration: Capability limits still apply. Benchmark your hardest prompts against GPT-5.6 Sol before assuming the balanced tier covers them, and check GPT-5.6 Luna for the high-volume tail where cost dominates. Pricing splits into short-context and long-context rates, so measure your real prompt sizes rather than an average.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use GPT 5.6 Terra

Best for

Everyday Production Traffic: Application features and internal tooling that run continuously at predictable cost
Mid-Tier Agent Steps: Routine planning, retrieval, and tool calls inside a longer agent run
Balanced Coding Work: Day-to-day development help, code review, and bug diagnosis
Long-Context Reading: Document sets and repositories that fit inside the context window without flagship pricing
Drop-In Tier Upgrade: A direct replacement for a mid-tier GPT-5.x model already in production

Consider alternatives when

Hardest Agentic Tasks: GPT-5.6 Sol is the flagship and the most capable model in the family
High-Volume Cost Control: GPT-5.6 Luna carries the lowest price in the GPT-5.6 family
Autonomous Coding Agents: GPT-5.x codex variants target sandboxed software engineering directly
Voice and Audio Input: The gpt-realtime family handles live speech, since GPT-5.6 models read text and images only

Copy link to headingConclusion

GPT 5.6 Terra is the tier most GPT-5.6 traffic belongs on: comparable performance to the previous generation at a lower price, with the family's agentic gains in coding, biology, and cybersecurity. Escalate to GPT-5.6 Sol for the hardest requests and drop to GPT-5.6 Luna where volume decides the budget.

Copy link to headingFrequently Asked Questions

What is GPT 5.6 Terra built for?
Everyday production work. OpenAI designed GPT 5.6 Terra to balance intelligence and cost, which puts it between the GPT-5.6 Sol flagship and the low-cost GPT-5.6 Luna tier.
How does GPT 5.6 Terra compare with the previous generation?
Performance compares to the previous generation at a lower price, and GPT 5.6 Terra handles agentic coding, biology, and cybersecurity work better. It also reaches answers in fewer tokens.
What context window and output limit does GPT 5.6 Terra support?
1.1M tokens, with up to 128K tokens of output per request, matching the rest of the GPT-5.6 family.
What inputs does GPT 5.6 Terra accept?
Text and images, with text output. Audio and video input are not supported, so route voice work to the gpt-realtime family instead.
Which APIs can I use to call GPT 5.6 Terra?
Set the model to openai/gpt-5.6-terra in the AI SDK, the Chat Completions API, the Responses API, or another supported API format. AI Gateway accepts each format and routes the request.
When should I escalate from GPT 5.6 Terra to GPT-5.6 Sol?
Escalate when the balanced tier misses on your hardest prompts. Log the turns where GPT 5.6 Terra falls short, retry those against GPT-5.6 Sol, and route only that traffic to the flagship.
What does GPT 5.6 Terra cost?
List pricing is $2 per million input tokens and $12 per million output tokens, with cached input at $0.2. Short-context and long-context requests are priced separately, and AI Gateway mirrors provider pricing with no markup.
Does GPT 5.6 Terra support zero data retention through AI Gateway?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

Your use is subject to OpenAI's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

GPT 5.6 Terra

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Fast mode

Copy link to headingMore models by OpenAI

Copy link to headingAbout GPT 5.6 Terra

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use GPT 5.6 Terra

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions