LLM models

GPT-5.6 Sol

On this page

Operations
Input parameters
Example request

GPT-5.6 — frontier reasoning and generation through one API.

modelId	gpt-5-6-sol
Modality	text
Pricing	See this model on the Pricing page for the current per-call price (with your markup).

Operations

Operation	modelId	Endpoint	Required input
Default	gpt-5-6-sol	POST /api/v1/generate	prompt
Poll task	—	GET /api/v1/task/{id}?model=gpt-5-6-sol	—

Input parameters

Field	Type	Required	Values / example
prompt	string	Yes	Text value (example: Read this function signature: transfer(from, to, amount, opts). List every input that would make it behave in a way the caller did not intend, ordered by how… — full value in the request example)
web_search	boolean	No	Web search feeds the results back as input tokens, so a searched turn typically costs many times a normal turn (measured: 6–87×). Billed per token as usual — nothing extra per search. (true/false) (example: false)
reasoning_effort	string	No	Control reasoning depth: Low for faster responses, High for deeper analysis (options: Low \| Medium \| High \| XHigh) (example: Medium)
stream	boolean	No	Send true to receive the reply as an event stream (Content-Type: text/event-stream). Omit it and you get a single JSON response — streaming is opt-in on this endpoint. (true/false) (example: true)
images	string[]	No	Up to 4 images per message — JPEG, PNG, GIF or WebP, 5 MB each. Send each one as a data: URL or an https URL. Images are billed as input tokens. (image URL)
max_tokens	number	No	Maximum response length in tokens, reasoning included. Leave empty for the default of 4,096. (range 1-128000)
system	string	No	System instruction for the model. Defaults to "You are GPT-5.6 Sol, developed by OpenAI." when omitted.
messages	array	No	A conversation instead of a single `prompt`: an array of { "role", "content" } objects, where role is user, assistant, system or tool (a function result, with `tool_call_id`); an assistant message may carry `tool_calls` instead of text — see `tools`. Send the whole conversation — we do not limit how many messages it has, and we do not drop old ones; the model's context window is the limit. Send `prompt` or `messages`, not both. Do not flatten a conversation into one prompt with "User:" / "Assistant:" labels — the model reads that as a single message, and a model using web search then searches for the whole block instead of your question.
tools	array	No	Functions the model may call, up to 64. Each is { "type": "function", "function": { "name", "description", "parameters" } } with `parameters` a JSON Schema object (the flat Responses form and Anthropic's { "name", "description", "input_schema" } are accepted too); `strict: true` is accepted. When the model calls one, the response carries `toolCalls`: run the function, then send the conversation back in `messages` with the assistant's `tool_calls` and one { "role": "tool", "tool_call_id", "content" } message per result — and the same `tools` again. Function calling cannot be combined with web search in the same request.
tool_choice	string \| object	No	`auto` (the model decides; the default when `tools` is set), `none` (no call), `required` (at least one call), or { "type": "function", "function": { "name" } } to require that function.

Example request

bash

curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"gpt-5-6-sol","input":{"prompt":"Read this function signature: transfer(from, to, amount, opts). List every input that would make it behave in a way the caller did not intend, ordered by how likely a real caller is to hit it. For each, say what the function should do instead. No code, just the cases and the intended behaviour, under 200 words.","web_search":false,"reasoning_effort":"Medium","stream":true,"images":["data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAIAAAACCAIAAAD91JpzAAAAFklEQVR4nGP8z4AATAxIHFQeMg8OAgB1yQIDpk8YwwAAAABJRU5ErkJggg=="],"max_tokens":4096}}'

GPT-5.6 Terra Wan 2.6