GPT 5.5
gpt-5.5Use the GPT 5.5 API for chat completions. Send a conversation prompt and receive a text response. Build chat assistants for question answering, summarization, and drafting. Compare the available provider routes, request examples, and usage prices on OpenAny.
- Published price
- From $5.000 / 1M tokens
- Billing unit
- / 1M tokens
- Context / Max output
- 1050K / 128K
- Listed routes
- 1
Other parameters (26)
Result preview
Tencent-Intl · 2303ms
Response example. Run to see the actual response.
{
"id": "gen-1784711098-OzCMHbzkUL7YzxIh1xVO",
"cost": {
"usd": 0,
"diem": 0.00010625
},
"model": "openai-gpt-56-luna",
"usage": {
"total_tokens": 20,
"prompt_tokens": 7,
"completion_tokens": 13,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"audio_tokens": 0,
"image_tokens": 0,
"reasoning_tokens": 0
}
},
"object": "chat.completion",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null
},
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "completed"
}
],
"created": 1784711098,
"service_tier": "default",
"openmodels_cost": 8,
"venice_parameters": {
"enable_e2ee": true,
"enable_x_search": false,
"disable_thinking": false,
"enable_web_search": "off",
"enable_web_scraping": false,
"enable_web_citations": false,
"web_search_citations": [],
"strip_thinking_response": false,
"include_venice_system_prompt": false,
"include_search_results_in_stream": false,
"return_search_results_as_documents": false
}
}- Base URL
https://api.openany.si/v1- POST
/v1/chat/completions- Authentication
Authorization: Bearer $OPENANY_API_KEY
Request parameters
| Parameter | Type / range | Default value | Required | Description |
|---|---|---|---|---|
messages | array | — | Yes | Chat conversation. Each message must match its role-specific structure. GPT-5.5 accepts text and image inputs. |
model | string | — | Yes | The model to use |
frequency_penalty | number · -2 ~ 2 | 0 | No | Penalty for repeated tokens |
logprobs | boolean | false | No | Return output token log probabilities. Must be true when top_logprobs is supplied. |
max_completion_tokens | integer · >= 1 | — | No | Upper limit for generated completion tokens, including visible output and reasoning tokens. |
max_tokens | integer · >= 1 | — | No | Deprecated completion token limit. Prefer max_completion_tokens. |
metadata | object | — | No | Up to 16 metadata entries. Keys allow 64 characters and values allow 512 characters. |
n | integer · 1 ~ 128 | 1 | No | Number of choices to generate |
parallel_tool_calls | boolean | true | No | Whether to allow the model to run tool calls in parallel. |
presence_penalty | number · -2 ~ 2 | 0 | No | Penalty for previously used tokens |
prompt_cache_key | string | — | No | Stable cache key used by OpenAI to improve prompt cache hit rates. Replaces the deprecated user field for caching. |
prompt_cache_retention | string · 24h | — | No | GPT-5.5 supports only 24h cache retention. This legacy field is deprecated in the current API reference. |
reasoning_effort | string · none | low | medium | high | xhigh | medium | No | GPT-5.5 reasoning effort. The default is medium. |
response_format | object | — | No | Chat output format. Use text, json_object, or a named json_schema configuration. |
route | object | — | No | OpenAny routing extension. Selects a supplier and other platform routing options. |
route_mode | string | — | No | OpenAny routing extension. Controls platform route selection. |
safety_identifier | string | — | No | Stable end-user safety identifier, up to 128 characters. Hash identifying information before sending it. |
seed | integer | — | No | Deprecated best-effort deterministic sampling seed. Determinism is not guaranteed. |
service_tier | string · auto | default | flex | scale | priority | auto | No | Processing tier used to serve the request. |
stop | string | array | — | No | Sequences that stop generation |
store | boolean | false | No | Store the Chat completion for distillation or evals. Defaults to false. |
stream | boolean | false | No | Whether to stream the response |
stream_options | object | — | No | Streaming options. Requires stream=true. |
temperature | number · 0 ~ 2 | 1 | No | Sampling temperature |
tool_choice | string | object | — | No | Tool selection mode, a named function/custom tool, or an allowed-tools configuration. |
tools | array | — | No | Chat function or custom tools, with protocol-specific nested definitions. |
top_logprobs | integer · 0 ~ 20 | — | No | Number of alternative token probabilities per position, from 0 to 20. Requires logprobs=true. |
top_p | number · 0 ~ 1 | 1 | No | Nucleus sampling probability |
user | string | — | No | Deprecated stable end-user identifier. Prefer safety_identifier and prompt_cache_key. |
verbosity | string · low | medium | high | medium | No | Controls response detail. The default is medium. |
Request example
curl 'https://api.openany.si/v1/chat/completions' \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{
"content": "Hello!",
"role": "user"
}
],
"model": "gpt-5.5",
"route_mode": "balanced",
"frequency_penalty": 0,
"logprobs": false,
"n": 1,
"parallel_tool_calls": true,
"presence_penalty": 0,
"reasoning_effort": "medium",
"service_tier": "auto",
"store": false,
"stream": false,
"temperature": 1,
"top_p": 1,
"verbosity": "medium"
}'Response example
Configured response example · not a live result
{
"id": "gen-1784711098-OzCMHbzkUL7YzxIh1xVO",
"cost": {
"usd": 0,
"diem": 0.00010625
},
"model": "openai-gpt-56-luna",
"usage": {
"total_tokens": 20,
"prompt_tokens": 7,
"completion_tokens": 13,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"audio_tokens": 0,
"image_tokens": 0,
"reasoning_tokens": 0
}
},
"object": "chat.completion",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null
},
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "completed"
}
],
"created": 1784711098,
"service_tier": "default",
"openmodels_cost": 8,
"venice_parameters": {
"enable_e2ee": true,
"enable_x_search": false,
"disable_thinking": false,
"enable_web_search": "off",
"enable_web_scraping": false,
"enable_web_citations": false,
"web_search_citations": [],
"strip_thinking_response": false,
"include_venice_system_prompt": false,
"include_search_results_in_stream": false,
"return_search_results_as_documents": false
}
}Error handling
400Check the model ID and request fields.429Retry with exponential backoff.5xxRetry only temporary provider failures.JSON Schema
{
"type": "object",
"allOf": [
{
"not": {
"anyOf": [
{
"required": [
"background"
]
},
{
"required": [
"context_management"
]
},
{
"required": [
"conversation"
]
},
{
"required": [
"include"
]
},
{
"required": [
"input"
]
},
{
"required": [
"instructions"
]
},
{
"required": [
"max_output_tokens"
]
},
{
"required": [
"max_tool_calls"
]
},
{
"required": [
"previous_response_id"
]
},
{
"required": [
"prompt"
]
},
{
"required": [
"reasoning"
]
},
{
"required": [
"text"
]
},
{
"required": [
"truncation"
]
}
]
}
},
{
"if": {
"required": [
"top_logprobs"
]
},
"then": {
"required": [
"logprobs"
],
"properties": {
"logprobs": {
"const": true
}
}
}
},
{
"if": {
"required": [
"stream_options"
]
},
"then": {
"required": [
"stream"
],
"properties": {
"stream": {
"const": true
}
}
}
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"messages"
],
"properties": {
"n": {
"type": "integer",
"default": 1,
"maximum": 128,
"minimum": 1,
"description": "Number of choices to generate"
},
"seed": {
"type": "integer",
"deprecated": true,
"description": "Deprecated best-effort deterministic sampling seed. Determinism is not guaranteed."
},
"stop": {
"type": [
"string",
"array"
],
"items": {
"type": "string"
},
"maxItems": 4,
"description": "Sequences that stop generation"
},
"user": {
"type": "string",
"deprecated": true,
"description": "Deprecated stable end-user identifier. Prefer safety_identifier and prompt_cache_key."
},
"model": {
"type": "string",
"description": "The model to use"
},
"route": {
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "OpenAny supplier name."
}
},
"description": "OpenAny routing extension. Selects a supplier and other platform routing options."
},
"store": {
"type": "boolean",
"default": false,
"description": "Store the Chat completion for distillation or evals. Defaults to false."
},
"tools": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"function"
],
"properties": {
"type": {
"const": "function"
},
"function": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]+$",
"maxLength": 64
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"type": "object"
},
"description": {
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"type",
"custom"
],
"properties": {
"type": {
"const": "custom"
},
"custom": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string"
},
"format": {
"oneOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"const": "text"
}
}
},
{
"type": "object",
"required": [
"type",
"grammar"
],
"properties": {
"type": {
"const": "grammar"
},
"grammar": {
"type": "object",
"required": [
"definition",
"syntax"
],
"properties": {
"syntax": {
"enum": [
"lark",
"regex"
],
"type": "string"
},
"definition": {
"type": "string"
}
}
}
}
}
]
},
"description": {
"type": "string"
}
}
}
}
}
]
},
"description": "Chat function or custom tools, with protocol-specific nested definitions."
},
"top_p": {
"type": "number",
"default": 1,
"maximum": 1,
"minimum": 0,
"description": "Nucleus sampling probability"
},
"stream": {
"type": "boolean",
"default": false,
"description": "Whether to stream the response"
},
"logprobs": {
"type": "boolean",
"default": false,
"description": "Return output token log probabilities. Must be true when top_logprobs is supplied."
},
"messages": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"name": {
"type": "string"
},
"role": {
"const": "system"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
"minItems": 1
}
]
}
}
},
{
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"name": {
"type": "string"
},
"role": {
"const": "developer"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
"minItems": 1
}
]
}
}
},
{
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"name": {
"type": "string"
},
"role": {
"const": "user"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
{
"type": "object",
"required": [
"type",
"image_url"
],
"properties": {
"type": {
"const": "image_url"
},
"image_url": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
},
"detail": {
"enum": [
"auto",
"low",
"high",
"original"
],
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"type",
"file"
],
"properties": {
"file": {
"type": "object",
"properties": {
"file_id": {
"type": "string"
},
"filename": {
"type": "string"
},
"file_data": {
"type": "string"
}
}
},
"type": {
"const": "file"
}
}
}
]
},
"minItems": 1
}
]
}
}
},
{
"type": "object",
"anyOf": [
{
"required": [
"content"
],
"properties": {
"content": {
"not": {
"type": "null"
}
}
}
},
{
"required": [
"tool_calls"
]
},
{
"required": [
"function_call"
],
"properties": {
"function_call": {
"type": "object"
}
}
}
],
"required": [
"role"
],
"properties": {
"name": {
"type": "string"
},
"role": {
"const": "assistant"
},
"content": {
"anyOf": [
{
"type": [
"string",
"null"
]
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
"minItems": 1
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"const": "refusal"
},
"refusal": {
"type": "string"
}
}
},
"maxItems": 1,
"minItems": 1
}
]
},
"refusal": {
"type": [
"string",
"null"
]
},
"tool_calls": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"required": [
"id",
"type",
"function"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"const": "function"
},
"function": {
"type": "object",
"required": [
"name",
"arguments"
],
"properties": {
"name": {
"type": "string"
},
"arguments": {
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"id",
"type",
"custom"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"const": "custom"
},
"custom": {
"type": "object",
"required": [
"name",
"input"
],
"properties": {
"name": {
"type": "string"
},
"input": {
"type": "string"
}
}
}
}
}
]
},
"minItems": 1
},
"function_call": {
"type": [
"object",
"null"
],
"required": [
"name",
"arguments"
],
"deprecated": true,
"properties": {
"name": {
"type": "string"
},
"arguments": {
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"role",
"tool_call_id",
"content"
],
"properties": {
"role": {
"const": "tool"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
"minItems": 1
}
]
},
"tool_call_id": {
"type": "string"
}
}
},
{
"type": "object",
"required": [
"role",
"name",
"content"
],
"deprecated": true,
"properties": {
"name": {
"type": "string"
},
"role": {
"const": "function"
},
"content": {
"type": [
"string",
"null"
]
}
}
}
]
},
"minItems": 1,
"description": "Chat conversation. Each message must match its role-specific structure. GPT-5.5 accepts text and image inputs."
},
"metadata": {
"type": "object",
"description": "Up to 16 metadata entries. Keys allow 64 characters and values allow 512 characters.",
"maxProperties": 16,
"propertyNames": {
"maxLength": 64
},
"additionalProperties": {
"type": "string",
"maxLength": 512
}
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string",
"default": "medium",
"description": "Controls response detail. The default is medium."
},
"max_tokens": {
"type": "integer",
"minimum": 1,
"deprecated": true,
"description": "Deprecated completion token limit. Prefer max_completion_tokens."
},
"route_mode": {
"type": "string",
"description": "OpenAny routing extension. Controls platform route selection."
},
"temperature": {
"type": "number",
"default": 1,
"maximum": 2,
"minimum": 0,
"description": "Sampling temperature"
},
"tool_choice": {
"type": [
"string",
"object"
],
"oneOf": [
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"function"
],
"properties": {
"type": {
"const": "function"
},
"function": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"type",
"custom"
],
"properties": {
"type": {
"const": "custom"
},
"custom": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string"
}
}
}
}
},
{
"type": "object",
"required": [
"type",
"allowed_tools"
],
"properties": {
"type": {
"const": "allowed_tools"
},
"allowed_tools": {
"type": "object",
"required": [
"mode",
"tools"
],
"properties": {
"mode": {
"enum": [
"auto",
"required"
],
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "object"
}
}
}
}
}
}
],
"description": "Tool selection mode, a named function/custom tool, or an allowed-tools configuration."
},
"service_tier": {
"enum": [
"auto",
"default",
"flex",
"scale",
"priority"
],
"type": "string",
"default": "auto",
"description": "Processing tier used to serve the request."
},
"top_logprobs": {
"type": "integer",
"maximum": 20,
"minimum": 0,
"description": "Number of alternative token probabilities per position, from 0 to 20. Requires logprobs=true."
},
"stream_options": {
"type": "object",
"properties": {
"include_usage": {
"type": "boolean"
},
"include_obfuscation": {
"type": "boolean"
}
},
"description": "Streaming options. Requires stream=true."
},
"response_format": {
"type": "object",
"oneOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"const": "text"
}
}
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"const": "json_object"
}
}
},
{
"type": "object",
"required": [
"type",
"json_schema"
],
"properties": {
"type": {
"const": "json_schema"
},
"json_schema": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]+$",
"maxLength": 64
},
"schema": {
"type": "object"
},
"strict": {
"type": [
"boolean",
"null"
]
},
"description": {
"type": "string"
}
}
}
}
}
],
"description": "Chat output format. Use text, json_object, or a named json_schema configuration."
},
"presence_penalty": {
"type": "number",
"default": 0,
"maximum": 2,
"minimum": -2,
"description": "Penalty for previously used tokens"
},
"prompt_cache_key": {
"type": "string",
"description": "Stable cache key used by OpenAI to improve prompt cache hit rates. Replaces the deprecated user field for caching."
},
"reasoning_effort": {
"enum": [
"none",
"low",
"medium",
"high",
"xhigh"
],
"type": "string",
"default": "medium",
"description": "GPT-5.5 reasoning effort. The default is medium."
},
"frequency_penalty": {
"type": "number",
"default": 0,
"maximum": 2,
"minimum": -2,
"description": "Penalty for repeated tokens"
},
"safety_identifier": {
"type": "string",
"maxLength": 128,
"description": "Stable end-user safety identifier, up to 128 characters. Hash identifying information before sending it."
},
"parallel_tool_calls": {
"type": "boolean",
"default": true,
"description": "Whether to allow the model to run tool calls in parallel."
},
"max_completion_tokens": {
"type": "integer",
"minimum": 1,
"description": "Upper limit for generated completion tokens, including visible output and reasoning tokens."
},
"prompt_cache_retention": {
"enum": [
"24h"
],
"type": "string",
"deprecated": true,
"description": "GPT-5.5 supports only 24h cache retention. This legacy field is deprecated in the current API reference."
}
}
}Request example
POST /v1/chat/completionscurl 'https://api.openany.si/v1/chat/completions' \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{
"content": "Hello!",
"role": "user"
}
],
"model": "gpt-5.5",
"route_mode": "balanced",
"frequency_penalty": 0,
"logprobs": false,
"n": 1,
"parallel_tool_calls": true,
"presence_penalty": 0,
"reasoning_effort": "medium",
"service_tier": "auto",
"store": false,
"stream": false,
"temperature": 1,
"top_p": 1,
"verbosity": "medium"
}'Model API questions
How do I call GPT 5.5 through OpenAny?
Use model ID gpt-5.5 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.
How is GPT 5.5 billed?
Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.
Are Community and Verified routes the same as an official publisher API?
No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.
Where do these prices come from, and when were they updated?
Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.
Use GPT 5.5 with your agent
Inspect endpoint contracts and confirm availability and pricing before a paid call.