Skip to main content
Core.Today
|
OpenAISlowUltra

GPT-5.5 Pro

Maximum-capability tier of the GPT-5.5 family (dated snapshot). Uses more compute to think longer and deliver the most reliable answers on the hardest reasoning, coding and analysis tasks. Served only via the OpenAI Responses API. $30/$180 per million tokens (no cached-input discount), flat across the full context window.

55,740/334,440credits
input / output ยท per 1M tokens
Maximum-capability GPT-5.5 tier
1.05M token context window
128K max output tokens
Extended thinking for hardest problems
Responses API only (no chat completions)
Native vision and function calling

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
1.1M
tokens
Max Output
128K
tokens
Training Cutoff
2025-12
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens55,740$37.16
Output Tokens334,440$222.96

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.5-pro-2026-04-23",
  "input": "Review this database migration plan for a zero-downtime rollout across 40 services and identify every failure mode with mitigations.",
  "max_output_tokens": 16000
}'

Parameters

ParameterTypeRequiredDefaultDescription
modelstringYesgpt-5.5-pro-2026-04-23Model identifier (dated snapshot id)
inputstring | arrayYes-Responses API input: a plain string or an array of input items (messages, tool results)
instructionsstringNo-System-level instructions for the run
max_output_tokensintegerNo-Maximum tokens in the response, including internal reasoning tokens (Responses API field; not max_tokens)
reasoningobjectNo-Reasoning options, e.g. { effort: "high" }
streambooleanNofalseEnable Server-Sent Events streaming

Examples

Hardest Reasoning

Maximum-effort analysis with GPT-5.5 Pro via the Responses API

curl -X POST "https://api.core.today/llm/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.5-pro-2026-04-23",
  "input": "Review this database migration plan for a zero-downtime rollout across 40 services and identify every failure mode with mitigations.",
  "max_output_tokens": 16000
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1 and use client.responses.create()
2Dated snapshot id - pin this exact id for reproducible behavior (the alias gpt-5.5-pro resolves to it)
3Served only via the Responses API (POST /llm/openai/v1/responses) โ€” chat completions is not supported for this model
4Reserve for the hardest problems - standard GPT-5.5 ($5/$30) is far cheaper for routine tasks
5Responses take longer due to extended internal thinking - budget generous max_output_tokens, reasoning tokens count toward the limit
6Flat pricing โ€” no long-context surcharge above 272K input tokens

Use Cases

Hardest multi-step reasoning problems
High-stakes code review and architecture
Scientific and mathematical analysis
Long-document synthesis at maximum quality