openai/gpt-5.5
1,050,000 context · $1.00 / M input tokens · $6.00 / M output tokens
GPT-5.5 is OpenAI's frontier model released on April 23, 2026, designed for complex professional workloads including agentic coding, computer use, and deep research.
2026-07-09 05:16:53 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-5.5",
"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-5.5
GPT-5.5 is OpenAI's frontier model released on April 23, 2026, designed for complex professional workloads including agentic coding, computer use, and deep research.
Building on GPT-5.4, GPT-5.5 delivers stronger reasoning, higher reliability with 60% fewer hallucinations, and improved token efficiency. It matches GPT-5.4 per-token latency while performing at a significantly higher level of intelligence, with a 1M+ token context window and support for text and image inputs.
Why It Looks Great
- Frontier-class reasoning with 88.7% SWE-bench Verified and 92.4% MMLU scores.
- 1M token context window for large-scale reasoning, coding, and multimodal workflows.
- 60% fewer hallucinations compared to GPT-5.4 with improved token efficiency.
- Three variants: standard, Thinking (extended reasoning), and Pro (highest accuracy).
- Same per-token latency as GPT-5.4 despite the intelligence leap.
Key Features
- Context Window: 1050000 tokens
- Max Input: 922000 tokens
- Max Output: 128000 tokens
- Vision: Supported
- Function Calling: Supported
- Thinking Mode: Supported (low / medium / high / xhigh effort levels)
- Variants: GPT-5.5, GPT-5.5 Thinking, GPT-5.5 Pro
Specifications
GPT 5.5 API Features for Developers
Use GPT 5.5 API on OurToken for API access, GPT 5.5 API pricing clarity, coding workflows, long context, and structured output.
API Access
Call GPT 5.5 API through OurToken's unified endpoint and keep your integration close to an OpenAI-compatible workflow. Teams can test GPT 5.5, compare provider options, and move from evaluation to production without rebuilding every API connection.
Pricing Clarity
Review GPT 5.5 API pricing before you scale high-volume traffic. OurToken surfaces input and output token costs, so teams searching for GPT 5.5 API price details can estimate spend for coding, research, and agent workloads.
Coding Workflows
Use GPT 5.5 for code review, debugging, refactoring, software planning, and agent-style engineering tasks. It also supports Codex-like workflows where users compare codex 5.5, gpt codex 5.5, codex 5.5 pricing, and codex pricing expectations.
Long Context
Use GPT 5.5 API when your application needs long documents, complex prompts, research notes, and code-heavy projects in one workflow. The large context window helps the model keep more instructions and evidence available during multi-step reasoning.
Multimodal Input
Send text and image inputs when your product needs visual context, document understanding, or multimodal analysis. GPT 5.5 API can support product teams building API features that combine language reasoning with image-based information.
Structured Output
Build cleaner application logic with function calling and structured responses. GPT 5.5 API can support workflows where your app needs predictable output formats, tool calls, and reliable responses for downstream automation.
How to Use GPT 5.5 API on OurToken
Start with an API key, choose GPT 5.5 API, compare pricing, then test coding, structured output, and production quality.
Generate API Key
Create an OurToken API key and store it in a secure server-side environment variable. This gives your backend a stable way to call GPT 5.5 API without exposing credentials in client-side code.
01Select Model ID
Use gpt-5.5 as the model value when sending chat completions requests. Keep the page focused on GPT 5.5 API access, and document the model ID clearly for developers who are comparing provider routes.
02Call Unified API
Send requests through the OurToken unified API endpoint with an OpenAI-compatible client. This lets teams test GPT 5.5, compare API behavior, and avoid rewriting code for each provider or routing option.
03Compare Pricing
Before production rollout, compare GPT 5.5 API pricing against expected request volume, prompt size, and output length. Use the displayed GPT 5.5 API price to estimate coding, research, and agent workflow costs.
04Configure Outputs
Add structured output rules, JSON schemas, or function calling when your app needs predictable responses. GPT 5.5 API can be tested with tool workflows before you connect it to production automation.
05Test Codex Workflows
Run representative coding tasks such as review, debugging, patch planning, and agent instructions. This is where codex 5.5, codex gpt 5.5, and gpt codex 5.5 search intent can be addressed without confusing the API setup.
06GPT 5.5 API FAQ
Answers about GPT 5.5 API pricing, access, coding workflows, Codex-related searches, ChatGPT Plus, and provider comparisons.
