scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

[Feat] Add gpt-image-1 cost tracking (#10241)

Browse source 
* add gpt-image-1

* add gpt-image-1 example to docs
This commit is contained in:
Ishaan Jaff 2025-04-23 12:20:55 -07:00 • committed by GitHub
parent a649f10e63
commit 36ee132514
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 150 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
docs/my-website/docs/image_generation.md
View file

@ -20,9 +20,9 @@ print(f"response: {response}")
```yaml
model_list:
- model_name: dall-e-2 ### RECEIVED MODEL NAME ###
- model_name: gpt-image-1 ### RECEIVED MODEL NAME ###
litellm_params: # all params accepted by litellm.image_generation()
model: azure/dall-e-2 ### MODEL NAME sent to `litellm.image_generation()` ###
model: azure/gpt-image-1 ### MODEL NAME sent to `litellm.image_generation()` ###
api_base: https://my-endpoint-europe-berri-992.openai.azure.com/
api_key: "os.environ/AZURE_API_KEY_EU" # does os.getenv("AZURE_API_KEY_EU")
rpm: 6 # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm)
@ -47,7 +47,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/images/generations' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-D '{
"model": "dall-e-2",
"model": "gpt-image-1",
"prompt": "A cute baby sea otter",
"n": 1,
"size": "1024x1024"
@ -104,7 +104,7 @@ Any non-openai params, will be treated as provider-specific params, and sent in
litellm_logging_obj=None,
custom_llm_provider=None,
- `model`: *string (optional)* The model to use for image generation. Defaults to openai/dall-e-2
- `model`: *string (optional)* The model to use for image generation. Defaults to openai/gpt-image-1
- `n`: *int (optional)* The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
@ -112,7 +112,7 @@ Any non-openai params, will be treated as provider-specific params, and sent in
- `response_format`: *string (optional)* The format in which the generated images are returned. Must be one of url or b64_json.
- `size`: *string (optional)* The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
- `size`: *string (optional)* The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for gpt-image-1. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
- `timeout`: *integer* - The maximum time, in seconds, to wait for the API to respond. Defaults to 600 seconds (10 minutes).
@ -148,13 +148,14 @@ Any non-openai params, will be treated as provider-specific params, and sent in
from litellm import image_generation
import os
os.environ['OPENAI_API_KEY'] = ""
response = image_generation(model='dall-e-2', prompt="cute baby otter")
response = image_generation(model='gpt-image-1', prompt="cute baby otter")
```
| Model Name | Function Call | Required OS Variables |
|----------------------|---------------------------------------------|--------------------------------------|
| dall-e-2 | `image_generation(model='dall-e-2', prompt="cute baby otter")` | `os.environ['OPENAI_API_KEY']` |
| gpt-image-1 | `image_generation(model='gpt-image-1', prompt="cute baby otter")` | `os.environ['OPENAI_API_KEY']` |
| dall-e-3 | `image_generation(model='dall-e-3', prompt="cute baby otter")` | `os.environ['OPENAI_API_KEY']` |
| dall-e-2 | `image_generation(model='dall-e-2', prompt="cute baby otter")` | `os.environ['OPENAI_API_KEY']` |
## Azure OpenAI Image Generation Models
@ -182,8 +183,9 @@ print(response)
| Model Name | Function Call |
|----------------------|---------------------------------------------|
| dall-e-2 | `image_generation(model="azure/<your deployment name>", prompt="cute baby otter")` |
| gpt-image-1 | `image_generation(model="azure/<your deployment name>", prompt="cute baby otter")` |
| dall-e-3 | `image_generation(model="azure/<your deployment name>", prompt="cute baby otter")` |
| dall-e-2 | `image_generation(model="azure/<your deployment name>", prompt="cute baby otter")` |
## OpenAI Compatible Image Generation Models

70
litellm/model_prices_and_context_window_backup.json
View file

@ -1437,6 +1437,76 @@
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai"
},
"gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0490417e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.59263611e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0172526e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.58945719e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0172526e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.58945719e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"gpt-4o-transcribe": {
"mode": "audio_transcription",
"input_cost_per_token": 0.0000025,

70
model_prices_and_context_window.json
View file

@ -1437,6 +1437,76 @@
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai"
},
"gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0490417e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1024-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.59263611e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0172526e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1024-x-1536/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.58945719e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"low/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.0172526e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"medium/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 4.0054321e-8,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"high/1536-x-1024/gpt-image-1": {
"mode": "image_generation",
"input_cost_per_pixel": 1.58945719e-7,
"output_cost_per_pixel": 0.0,
"litellm_provider": "openai",
"supported_endpoints": ["/v1/images/generations"]
},
"gpt-4o-transcribe": {
"mode": "audio_transcription",
"input_cost_per_token": 0.0000025,