OpenAI: GPT-5.6 Terra

Balanced GPT-5.6 model for capable, cost-efficient everyday work

gpt-5.6-terra

AvailableOpenAIChatCached input 90% less

Input / Output-70%: $2.00 / $12.00$0.60 / $3.60
Context: 1.05M
Released: Jun 26, 2026
Max output: 128K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

About GPT-5.6 Terra

GPT-5.6 Terra is the balanced middle model of OpenAI's GPT-5.6 family, aimed at capable everyday work at a lower cost than the flagship. It reads text and images, calls tools, returns structured JSON, and has adjustable reasoning. OpenAI positions it as competitive with GPT-5.5 at a lower cost, which makes it the default pick when Luna is too light and Sol is more than needed.

Where it works well

Balances capability and cost, covering most coding and writing jobs without flagship overhead.
OpenAI positions it as competitive with GPT-5.5 while costing less, so it can replace that model on routine workloads.
Handles image input, tool calls, and schema-checked JSON in a single request.
Adjustable reasoning lets one deployment cover quick replies and slower analytical turns.

When to choose another model

Sol remains the choice for the hardest coding, scientific, and long-running agent tasks in this family.
The GPT-5.6 family is now marked legacy in OpenAI's guidance, and new projects are pointed to GPT-6 models.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.
02
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses API
POST/v1/responses
API format:
```
curl https://api.tokenlab.sh/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "gpt-5.6-terra",
    "input": "Hello!"
  }'
```

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Input tokens <= 272K

per 1M tokens

Official price: Input $2.00 / Output $12.00 / Cache read $0.20 / Cache write $2.50
Verified price: Input $0.60 / Output $3.60 / Cache read $0.06 / Cache write $0.75
Discount: -70%

Input tokens 272K-1.05M

per 1M tokens

Official price: Input $4.00 / Output $18.00 / Cache read $0.40 / Cache write $5.00
Verified price: Input $1.20 / Output $5.40 / Cache read $0.12 / Cache write $1.50
Discount: -70%

Prompt cache pricing

Cache read

Official price: $0.20
Verified price: $0.06
Discount: -70%

Cache write

Official price: $2.50
Verified price: $0.75
Discount: -70%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.01/search
Verified price: $0.003/search
Discount: -70%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Input tokens <= 272K	Input $2.00 / Output $12.00 / Cache read $0.20 / Cache write $2.50	Input $0.60 / Output $3.60 / Cache read $0.06 / Cache write $0.75	-70%
Input tokens 272K-1.05M	Input $4.00 / Output $18.00 / Cache read $0.40 / Cache write $5.00	Input $1.20 / Output $5.40 / Cache read $0.12 / Cache write $1.50	-70%
Prompt cache pricing
Cache read	$0.20	$0.06	-70%
Cache write	$2.50	$0.75	-70%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.01/search	$0.003/search	-70%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 11, 2026, 12:04 AM UTC

30-day success rate: 95.8%
7-day median latency: 13 sn=359
7-day P95 latency: 56.5 sn=359
30-day requests: 2K+
Last active: 42 minutes ago

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GPT-5.6 Terra in Console with a prompt ready to edit or send.

Help me try gpt-5.6-terra with a short message at /v1/responses. Show the reply, latency, and cost.

Use cases

Best for

Code
Reasoning
Vision

Everyday coding help
Review pull requests, explain unfamiliar code, and draft tests in an editor assistant that needs more care than a small model gives.
Document question answering
Answer questions over reports and manuals, with images or tables included, and return the result in a fixed JSON shape.
Support triage with tools
Look up an account, read the customer's message, and draft a reply, calling internal functions along the way.
Content drafting
Produce first drafts of emails, summaries, and product copy that an editor then tightens.

Prompt examples

Review this diff for bugs and confusing naming, then list the three changes you would make before merging.

Using the attached PDF text, answer which warranty terms apply to a unit bought in March, and quote the clause.

Draft a polite reply to this customer, look up the order status with the lookup tool first, and keep it under 120 words.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is GPT-5.6 Terra?

GPT-5.6 Terra is OpenAI's balanced tier in the GPT-5.6 family, between the flagship Sol and the lightweight Luna. It targets capable, cost-conscious everyday work with text and image input, tools, and structured output.

When should I pick Terra instead of Sol?

Pick Terra when tasks are ordinary: drafting, review, support, moderate coding. Move to Sol when long autonomous runs, hard debugging, or scientific analysis keep failing at Terra's level.

How does Terra compare with GPT-5.5?

OpenAI describes Terra as competitive with GPT-5.5 at a lower cost. Run your own test set before swapping, because the fit depends on the task.

Does GPT-5.6 Terra accept images and tool calls?

Yes, both are supported. It reads images alongside text, handles function calling, and can return JSON that follows a supplied schema. Its output is text only, not images or audio.

Is GPT-5.6 Terra still the recommended model?

OpenAI's guidance now lists GPT-5.6 models as legacy and recommends the GPT-6 family for new work. Terra stays callable, so existing integrations keep working while you plan a migration.

How much does GPT-5.6 Terra cost?

On TokenLab, GPT-5.6 Terra costs Input $0.60 / Output $3.60 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of GPT-5.6 Terra?

GPT-5.6 Terra accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens in one response.

Which endpoint should GPT-5.6 Terra use?

Use https://api.tokenlab.sh/v1/responses for GPT-5.6 Terra. The request example below shows the matching code shape.

Which operations does GPT-5.6 Terra support?

GPT-5.6 Terra supports Text to text. Select an operation above to see its endpoint and request example.