openai/gpt-5.6-terra
250K context · $0.50 / M input tokens · $3.00 / M output tokens
GPT-5.6 Terra is the balanced GPT-5.6 route for developers who want strong reasoning and coding capability with lower token costs than Sol.
Explore GPT-5.6 models
2026-07-10 07:18:48 UTC
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
API Access Guide
Code examples
Use the OurToken API endpoint for this model. The examples below use direct HTTP requests and the recommended endpoint for the model family.
curl https://api.ourtoken.ai/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-5.6-terra",
"input": "Hello!",
"max_output_tokens": 256
}'Responses API Reference
Create a model response with the OpenAI Responses-compatible endpoint. This format supports text input, message arrays, tools, reasoning controls, and multi-turn response continuation.
Authorization
| Content-Type | application/json |
| Authorization | Bearer YOUR_API_KEY |
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to call. |
| input | string | array<object> | Optional | Input content as a string or a structured message array. |
| instructions | string | Optional | System or developer instructions applied to the response. |
| max_output_tokens | integer | Optional | Maximum number of output tokens the model may generate. |
| temperature | number | Optional | Sampling temperature. |
| top_p | number | Optional | Nucleus sampling parameter. |
| stream | boolean | Optional | Whether to return a streaming response. |
| tools | array<object> | Optional | Tools available to the model. |
| tool_choice | string | object | Optional | Controls how the model selects tools. |
| reasoning | object | Optional | Reasoning configuration for models that support it. |
| previous_response_id | string | Optional | Previous response ID for continuing a conversation. |
| truncation | "auto" | "disabled" | Optional | Controls automatic context truncation. |
Response Body
| Field | Type | Required | Description |
|---|---|---|---|
| id | string | Required | Unique response identifier. |
| object | "response" | Required | Object type returned by the Responses API. |
| created_at | integer | Required | Unix timestamp when the response was created. |
| status | string | Required | Response lifecycle status. |
| model | string | Required | Model that produced the response. |
| output | array<object> | Required | Array of output items returned by the model. |
| output[].content[].text | string | Optional | Text content inside an output message item. |
| usage | object | Optional | Token usage information for the response. |
| usage.prompt_tokens | integer | Optional | Input token count. |
| usage.completion_tokens | integer | Optional | Output token count. |
| usage.total_tokens | integer | Optional | Total token count. |
| usage.prompt_tokens_details | object | Optional | Breakdown of input token usage. |
| usage.prompt_tokens_details.cached_tokens | integer | Optional | Tokens served from cache. |
| usage.prompt_tokens_details.text_tokens | integer | Optional | Text token count. |
| usage.prompt_tokens_details.audio_tokens | integer | Optional | Audio token count. |
| usage.prompt_tokens_details.image_tokens | integer | Optional | Image token count. |
| usage.completion_tokens_details | object | Optional | Breakdown of output token usage. |
| usage.completion_tokens_details.text_tokens | integer | Optional | Text token count. |
| usage.completion_tokens_details.audio_tokens | integer | Optional | Audio token count. |
| usage.completion_tokens_details.reasoning_tokens | integer | Optional | Reasoning token count. |
Model Introduction
OpenAI gpt-5.6-terra
GPT-5.6 Terra is the balanced GPT-5.6 route for developers who want strong reasoning and coding capability with lower token costs than Sol.
GPT 5.6 Terra API targets production workloads that need a practical balance of capability, latency, and price. OurToken exposes gpt-5.6-terra through an OpenAI-compatible API with clear input, output, cached input, and cache write pricing.
Why It Looks Great
- Balanced capability and cost within the GPT-5.6 family.
- Suitable for coding, structured analysis, assistants, and tool-calling applications.
- 250K context and up to 128K output for substantial production requests.
- Lower gpt 5.6 price than Sol while retaining the same family interface.
- Simple OpenAI gpt 5.6 integration through the OurToken unified API.
Key Features
- Model ID: gpt-5.6-terra
- Context Window: 250000 tokens
- Max Output: 128000 tokens
- Input: Text and Image
- Output: Text
- Function Calling: Supported
- OurToken Price: $0.50/M input, $0.05/M cached input, $0.625/M cache writes, $3/M output
Specifications
GPT 5.6 Terra API Features for Balanced Production
Use GPT 5.6 Terra for coding, reasoning, long-context assistants, tools, and predictable gpt 5.6 price planning.
Balanced GPT-5.6 Route
Terra sits between Sol and Luna for teams that need capable reasoning and coding without paying the flagship Sol price for every request.
Production Coding
Use GPT 5.6 Terra API for code generation, debugging, review, documentation, structured transformations, and application assistants.
250K Context Window
Keep substantial code, documents, conversation history, and instructions available while generating outputs up to 128K tokens.
Lower Token Pricing
OurToken gpt 5.6 price for Terra is $0.50/M input, $0.05/M cached input, $0.625/M cache writes, and $3/M output.
Shared Family Integration
Use the same Responses API integration across gpt 5.6 sol terra luna routes and change only the model ID during evaluation.
Practical Comparisons
Run gpt 5.6 sol vs terra and gpt 5.6 terra vs gpt 5.5 tests with identical prompts to compare quality, latency, and total cost.
How to Use GPT 5.6 Terra API on OurToken
Create an API key, choose gpt-5.6-terra, call the Responses API, and test Terra against Sol, Luna, and GPT-5.5.
Create an OurToken Key
Generate an API key in the dashboard and keep it in a secure server-side secret.
01Set the Terra Model ID
Use gpt-5.6-terra in the model field to select the balanced GPT 5.6 Terra API route.
02Send a Responses Request
Call the OpenAI-compatible Responses endpoint with input, instructions, streaming, tools, and output limits.
03Plan Cache Usage
Cached input costs $0.05/M and cache writes cost $0.625/M, reducing repeated prompt expense.
04Benchmark Your Workload
Measure task success, output quality, latency, and tokens on representative production prompts.
05Choose a Family Default
Compare Sol for maximum capability, Terra for balance, and Luna for lowest cost.
06GPT 5.6 Terra API FAQ
Answers about GPT 5.6 Terra access, release, price, Sol vs Terra, Terra vs GPT 5.5, caching, and model selection.