gpt-image-2

Azure · image_generation model

Input

$5.0000 / 1M tokens

Output

$10.0000 / 1M tokens

Cached input

$1.2500 / 1M tokens

Context

N/A

Pricing

Item	Raw value (per token)	Normalized
Input	0.000005	$5.0000 / 1M tokens
Output	0.00001	$10.0000 / 1M tokens
Cached input	0.00000125	$1.2500 / 1M tokens
Embedding	0.000005	$5.0000 / 1M tokens

Token limits

Capabilities

Capability	Supported
Vision	Yes
Function calling	No
Parallel function calling	No
Tool choice	No
Prompt caching	No
Reasoning	No
Response schema	No
System messages	No
Audio input	No
Audio output	No
Web search	No
PDF input	Yes
Video input	No

Similar models

Models with comparable pricing in the same mode (image_generation).

Model	Provider	Input	Output	Context	Coding	Features
gpt-image-2-2026-04-21	Azure	$5.0000 / 1M tokens	$10.0000 / 1M tokens	N/A	N/A	Vision
gpt-image-1.5	OpenAI	$5.0000 / 1M tokens	$10.0000 / 1M tokens	N/A	N/A	Vision
gpt-image-1.5-2025-12-16	OpenAI	$5.0000 / 1M tokens	$10.0000 / 1M tokens	N/A	N/A	Vision
gpt-image-2	OpenAI	$5.0000 / 1M tokens	$10.0000 / 1M tokens	N/A	N/A	Vision
gpt-image-2-2026-04-21	OpenAI	$5.0000 / 1M tokens	$10.0000 / 1M tokens	N/A	N/A	Vision
gemini-3-pro-image-preview	vertex_ai-language-models	$2.0000 / 1M tokens	$12.0000 / 1M tokens	32.8K	N/A	Vision Cache

Sources

Pricing source	LiteLLM model cost map
Synced at	2026-05-27
Manual review	Not reviewed

Raw LiteLLM fields

{
  "cache_read_input_image_token_cost": 0.000002,
  "cache_read_input_token_cost": 0.00000125,
  "input_cost_per_token": 0.000005,
  "input_cost_per_image_token": 0.000008,
  "litellm_provider": "azure",
  "mode": "image_generation",
  "output_cost_per_token": 0.00001,
  "output_cost_per_image_token": 0.00003,
  "supported_endpoints": [
    "/v1/images/generations",
    "/v1/images/edits"
  ],
  "supports_vision": true,
  "supports_pdf_input": true
}