> ## Documentation Index
> Fetch the complete documentation index at: https://api-tools.memories.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# GPT Image
> Generate chat completions using GPT ILM model with image inputs.
**Product**: Visual Intelligence — Image Model APIs (atomic)
**Use case**: Call an Image Language Model (Gemini / GPT / Nova / Qwen) directly with your own prompt. Full control over model and parameters.
**Host**: `https://mavi-backend.memories.ai/serve/api/v2`
**Auth**: `Authorization: sk-mavi-...` (no `Bearer` prefix)
This endpoint allows you to generate chat completions with image inputs using GPT ILM model.
**Endpoint:** `POST https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions`
Image Understanding (ILM) endpoints use the `/iu` path prefix. Video Understanding (VLM) endpoints use `/vu` instead.
## Supported Models
All models require the `gpt:` prefix when used in the `model` parameter (e.g., `gpt:gpt-4o`).
### GPT-5 Series (Latest)
| Model | Input Price | Output Price |
| ------------------------- | ---------------- | --------------- |
| **gpt-5.2** | \$1.75/1M tokens | \$14/1M tokens |
| **gpt-5.2-2025-12-11** | \$1.75/1M tokens | \$14/1M tokens |
| **gpt-5.2-chat-latest** | \$1.75/1M tokens | \$14/1M tokens |
| **gpt-5.1** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5.1-2025-11-13** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5.1-chat-latest** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5-2025-08-07** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5-chat-latest** | \$1.25/1M tokens | \$10/1M tokens |
| **gpt-5-mini** | \$0.25/1M tokens | \$2/1M tokens |
| **gpt-5-mini-2025-08-07** | \$0.25/1M tokens | \$2/1M tokens |
| **gpt-5-nano** | \$0.05/1M tokens | \$0.4/1M tokens |
| **gpt-5-nano-2025-08-07** | \$0.05/1M tokens | \$0.4/1M tokens |
### O-Series (Reasoning Models)
| Model | Input Price | Output Price |
| ---------------------- | --------------- | --------------- |
| **o1** | \$15/1M tokens | \$60/1M tokens |
| **o1-2024-12-17** | \$15/1M tokens | \$60/1M tokens |
| **o3** | \$2/1M tokens | \$8/1M tokens |
| **o3-2025-04-16** | \$2/1M tokens | \$8/1M tokens |
| **o4-mini** | \$1.1/1M tokens | \$4.4/1M tokens |
| **o4-mini-2025-04-16** | \$1.1/1M tokens | \$4.4/1M tokens |
### GPT-4.1 Series
| Model | Input Price | Output Price |
| --------------------------- | --------------- | --------------- |
| **gpt-4.1** | \$2/1M tokens | \$8/1M tokens |
| **gpt-4.1-2025-04-14** | \$2/1M tokens | \$8/1M tokens |
| **gpt-4.1-mini** | \$0.4/1M tokens | \$1.6/1M tokens |
| **gpt-4.1-mini-2025-04-14** | \$0.4/1M tokens | \$1.6/1M tokens |
| **gpt-4.1-nano** | \$0.1/1M tokens | \$0.4/1M tokens |
| **gpt-4.1-nano-2025-04-14** | \$0.1/1M tokens | \$0.4/1M tokens |
### GPT-4o Series
| Model | Input Price | Output Price |
| -------------------------- | ---------------- | ---------------- |
| **gpt-4o** | \$2.5/1M tokens | \$10/1M tokens |
| **gpt-4o-2024-08-06** | \$2.5/1M tokens | \$10/1M tokens |
| **gpt-4o-2024-05-13** | \$5/1M tokens | \$15/1M tokens |
| **chatgpt-4o-latest** | \$5/1M tokens | \$15/1M tokens |
| **gpt-4o-mini** | \$0.15/1M tokens | \$0.60/1M tokens |
| **gpt-4o-mini-2024-07-18** | \$0.15/1M tokens | \$0.60/1M tokens |
### GPT-4 Turbo
| Model | Input Price | Output Price |
| -------------------------- | -------------- | -------------- |
| **gpt-4-turbo** | \$10/1M tokens | \$30/1M tokens |
| **gpt-4-turbo-2024-04-09** | \$10/1M tokens | \$30/1M tokens |
**Pricing Notes:**
* All prices are per 1 million tokens
* GPT-5 series offers the latest capabilities with improved performance
* O-series models are optimized for complex reasoning tasks
* GPT-4.1 and GPT-4o provide balanced performance and cost
* Mini and Nano variants offer cost-effective alternatives
* Remember to include the `gpt:` prefix: `"model": "gpt:gpt-4o"`
### Request Body
| Parameter | Type | Required | Default | Description |
| ------------------ | ----------------------- | -------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| model | string | Yes | - | The model to use (e.g., `gpt:gpt-4o`) |
| messages | array | Yes | - | Array of message objects. Each message contains:
- `role`: Role type, values: `system`, `user`, `assistant`
- `content`: Message content, can be a string or array. Array items can contain:
- `type`: Content type, `text` or `image_url`
- `text`: Text content (when type is text)
- `image_url`: Image object (when type is image\_url)
- `url`: Image URL or base64 encoded image |
| response\_format | object | No | - | Force JSON output format. Contains `type` field with value `json_object` |
| temperature | number | No | 0 | Controls randomness: 0.0-2.0, 0 = deterministic |
| max\_tokens | integer | No | 1000 | Maximum number of tokens to generate |
| top\_p | number | No | 1.0 | Nucleus sampling: 0.0-1.0, consider tokens with top\_p probability mass |
| frequency\_penalty | number | No | 0.0 | Reduces repetition of frequent tokens: -2.0 to 2.0 |
| presence\_penalty | number | No | 0.0 | Increases likelihood of new topics: -2.0 to 2.0 |
| n | integer | No | 1 | Number of completions to generate |
| stream | boolean | No | false | Whether to stream the response |
| stop | string \| array \| null | No | null | Stop sequences. Can be a string, array of strings, or null |
### Code Example
```python Python theme={null}
from openai import OpenAI
client = OpenAI(
api_key="sk-mavi-...",
base_url="https://mavi-backend.memories.ai/serve/api/v2/iu"
)
def call_my_ilm():
resp = client.chat.completions.create(
model="gpt:gpt-4o",
messages=[
{"role": "system", "content": "You are a multimodal assistant. Only output JSON, do not output any extra text."},
{
"role": "user",
"content": [
{
"type": "text",
"text": """
Please analyze the image and strictly output the following JSON structure (all fields must be present, use null or empty array for missing values):
{
"title": string,
"summary": string,
"objects": [
{"name": string, "count": integer, "confidence": number}
],
"scene": string,
"warnings": [string]
}
Note:
- Only output JSON
- No Markdown
- No explanation of the process
"""
},
{
"type": "image_url",
"image_url": {
"url": "https://storage.googleapis.com/memories-test-data/gun5.png" # base64 or url
}
}
]
}
],
response_format={"type": "json_object"}, # Force JSON output format
temperature=0, # Controls randomness: 0.0-2.0, 0 = deterministic
max_tokens=1000, # Maximum number of tokens to generate
top_p=1.0, # Nucleus sampling: 0.0-1.0, consider tokens with top_p probability mass
frequency_penalty=0.0, # -2.0 to 2.0, reduces repetition of frequent tokens
presence_penalty=0.0, # -2.0 to 2.0, increases likelihood of new topics
n=1, # Number of completions to generate
stream=False, # Whether to stream the response
stop=None # Stop sequences (list of strings)
)
return resp
# Usage example
result = call_my_ilm()
print(result)
```
### Response
Returns the chat completion response with JSON format.
```json theme={null}
{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "gpt-4o-2024-08-06",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "{\"title\": \"Image Title\", \"summary\": \"Image summary...\", \"objects\": [{\"name\": \"object1\", \"count\": 1, \"confidence\": 0.95}], \"scene\": \"indoor\", \"warnings\": []}",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 447,
"completion_tokens": 112,
"total_tokens": 559,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default",
"system_fingerprint": "fp_deacdd5f6f"
}
```
### Response Parameters
| Parameter | Type | Description |
| -------------------------------------------------------------- | -------------- | -------------------------------------------------- |
| id | string | Unique identifier for the chat completion |
| object | string | Object type, always "chat.completion" |
| created | integer | Unix timestamp of when the completion was created |
| model | string | The model used for the completion |
| choices | array | Array of completion choices |
| choices\[].index | integer | Index of the choice in the choices array |
| choices\[].message | object | Message object containing the assistant's response |
| choices\[].message.role | string | Role of the message, always "assistant" |
| choices\[].message.content | string | Content of the message |
| choices\[].message.refusal | string \| null | Refusal message if the request was refused |
| choices\[].message.annotations | array | Annotations for the message |
| choices\[].logprobs | object \| null | Log probability information |
| choices\[].finish\_reason | string | Reason why the completion finished |
| usage | object | Token usage information |
| usage.prompt\_tokens | integer | Number of tokens in the prompt |
| usage.completion\_tokens | integer | Number of tokens in the completion |
| usage.total\_tokens | integer | Total number of tokens used |
| usage.prompt\_tokens\_details | object | Detailed prompt token information |
| usage.prompt\_tokens\_details.cached\_tokens | integer | Number of cached tokens |
| usage.prompt\_tokens\_details.audio\_tokens | integer | Number of audio tokens |
| usage.completion\_tokens\_details | object | Detailed completion token information |
| usage.completion\_tokens\_details.reasoning\_tokens | integer | Number of reasoning tokens |
| usage.completion\_tokens\_details.audio\_tokens | integer | Number of audio tokens |
| usage.completion\_tokens\_details.accepted\_prediction\_tokens | integer | Number of accepted prediction tokens |
| usage.completion\_tokens\_details.rejected\_prediction\_tokens | integer | Number of rejected prediction tokens |
| service\_tier | string | The service tier used for the request |
| system\_fingerprint | string | System fingerprint for the model version |
## OpenAPI
````yaml visual-intelligence/gpt/openapi.json POST /iu/chat/completions
openapi: 3.1.0
info:
title: GPT API Reference
description: REST APIs for GPT ILM model
version: v1.0.0
servers:
- url: https://mavi-backend.memories.ai/serve/api/v2
security:
- ApiKeyAuth: []
paths:
/iu/chat/completions:
post:
summary: Chat Completions GPT
description: Generate chat completions using GPT ILM model with image inputs.
operationId: chat_completions_gpt_ilm
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
model:
type: string
description: The model to use (e.g., gpt:gpt-4o)
example: gpt:gpt-4o
messages:
type: array
description: Array of message objects
items:
type: object
properties:
role:
type: string
enum:
- system
- user
- assistant
content:
oneOf:
- type: string
- type: array
items:
type: object
properties:
type:
type: string
enum:
- text
- image_url
text:
type: string
image_url:
type: object
properties:
url:
type: string
description: URL or base64 encoded image
required:
- url
required:
- role
- content
response_format:
type: object
properties:
type:
type: string
enum:
- json_object
description: Force JSON output format
temperature:
type: number
description: 'Controls randomness: 0.0-2.0, 0 = deterministic'
minimum: 0
maximum: 2
default: 0
max_tokens:
type: integer
description: Maximum number of tokens to generate
default: 1000
top_p:
type: number
description: 'Nucleus sampling: 0.0-1.0'
minimum: 0
maximum: 1
default: 1
frequency_penalty:
type: number
description: 'Reduces repetition of frequent tokens: -2.0 to 2.0'
minimum: -2
maximum: 2
default: 0
presence_penalty:
type: number
description: 'Increases likelihood of new topics: -2.0 to 2.0'
minimum: -2
maximum: 2
default: 0
'n':
type: integer
description: Number of completions to generate
default: 1
stream:
type: boolean
description: Whether to stream the response
default: false
stop:
oneOf:
- type: string
- type: array
items:
type: string
- type: 'null'
description: Stop sequences
required:
- model
- messages
responses:
'200':
description: Chat completion response with JSON format
content:
application/json:
schema:
type: object
properties:
id:
type: string
example: chatcmpl-CsRhYgDaLSNjl80v5uYBufEDbJqAM
object:
type: string
example: chat.completion
created:
type: integer
example: 1767092232
model:
type: string
example: gpt-4o-2024-08-06
description: The model used for the completion
choices:
type: array
items:
type: object
properties:
index:
type: integer
message:
type: object
properties:
role:
type: string
enum:
- assistant
content:
type: string
description: The message content
refusal:
type:
- string
- 'null'
description: Refusal message if the request was refused
example: null
annotations:
type: array
description: Annotations for the message
items:
type: object
example: []
required:
- role
- content
logprobs:
type:
- object
- 'null'
description: Log probability information
example: null
finish_reason:
type: string
example: stop
required:
- index
- message
- finish_reason
usage:
type: object
properties:
prompt_tokens:
type: integer
example: 447
completion_tokens:
type: integer
example: 112
total_tokens:
type: integer
example: 559
prompt_tokens_details:
type: object
properties:
cached_tokens:
type: integer
example: 0
audio_tokens:
type: integer
example: 0
completion_tokens_details:
type: object
properties:
reasoning_tokens:
type: integer
example: 0
audio_tokens:
type: integer
example: 0
accepted_prediction_tokens:
type: integer
example: 0
rejected_prediction_tokens:
type: integer
example: 0
required:
- prompt_tokens
- completion_tokens
- total_tokens
service_tier:
type: string
example: default
description: The service tier used for the request
system_fingerprint:
type: string
example: fp_deacdd5f6f
description: System fingerprint for the model version
required:
- id
- object
- created
- model
- choices
- usage
components:
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: Authorization
````