Regularly updated list of AI providers and models, available for multiple languages and platforms, such as OpenAI and Gemini.
APIs available for:
| Language | Package |
|---|---|
| Python | ai_providers_and_models |
| Node.JS | @dwmkerr/ai-providers-and-models |
Note
This project is in the early stages, the API will most likely change. Please contribute or share if you can!
The models.yaml file contains details of available OpenAI models and their capabilities, you can download it and use it directly. There are also Node.JS and Python APIs.
A short snippet is below - the models.yaml file is more complete.
version: 0.1.9
updated: 2025-03-26T00:00:00.000Z
providers:
openai:
id: openai
name: OpenAI
docs: https://platform.openai.com/docs/models
api_specification: api.openai.com/v1
base_url: https://api.openai.com/v1/
models:
gpt-4o:
id: gpt-4o
name: GPT-4o
documentation_url: https://platform.openai.com/docs/models/gpt-4o
description_short: Fast, intelligent, flexible GPT model
description: >-
GPT-4o ("o" for "omni") is our versatile, high-intelligence flagship
model. It accepts both text and image inputs, and produces text
outputs (including Structured Outputs). It is the best model for most
tasks, and is our most capable model outside of our o-series models.
status: general-availability
knowledgeCutoff: October 2023
context_window: 128000
max_output_tokens: 16384
validated: true
pricing:
input_per_million: 2.5
output_per_million: 10
modalities:
text: true
image: false
audio: false
video: false
endpoints:
assistants: true
batch: false
chat_completions: true
completions_legacy: false
embeddings: false
fine_tuning: true
image_generation: false
moderation: false
realtime: false
responses: true
speech_generation: false
transcription: false
translation: false
versions:
- id: gpt-4o-2024-08-06
release_date: "2024-08-06"
isDefault: true
isDeprecated: false
description: Current version of GPT-4o, released August 2024
- id: gpt-4o-2024-11-20
release_date: "2024-11-20"
isDefault: false
isDeprecated: false
description: Latest version of GPT-4o, released November 2024
- id: gpt-4o-2024-05-13
release_date: "2024-05-13"
isDefault: false
isDeprecated: true
description: Previous version of GPT-4o, released May 2024 and now deprecated- Model Versioning: Track multiple versions of models with deprecation status and default versions. See versioning documentation for details.
- Provider Support: Multiple AI providers including OpenAI and Gemini
- Cross-Platform: Available for Node.js and Python
- Regular Updates: Models and capabilities are regularly updated
Model and provider data can be loaded programmatically for Node.JS and Python.
Installation:
npm install @dwmkerr/ai-providers-and-modelsUsage:
import { providers } from "@dwmkerr/ai-providers-and-models";
// Loop through each provider and its models...
for (const providerId of Object.keys(providers)) {
const provider = providers[providerId];
for (const modelId of Object.keys(provider.models)) {
const model = provider.models[modelId];
console.log(model.name);
}
}
// ...or get more complex info!
const model = providers["openai"].models["gpt-4.5-preview"];
print(model.pricing.input_per_million)Detailed documentation at: modules/node/README.md
Installation:
pip install ai_providers_and_modelsUsage:
from ai_providers_and_models import providers
# Loop through each provider and its models...
for provider in providers.values():
print(provider.name)
for model_id, model in provider.models.items():
indent = " "
# Print the model name in green bold followed by a grey description.
print(f" {model.id} - {model.name}")
# ...or get more complex info!
model = providers["gemini"].models["models/gemini-2.0-flash"]
print(model.pricing.input_per_million)
print(model.modalities)Detailed documentation at: modules/python/README.md
The following models have been validated:
- ✅ indicates that I have checked the features, pricing and context limits, however, there is always room for human error so be particularly careful and double check pricing.
- 🧠 indicates has been at least partly tested using Terminal AI and should work for chat and completion API calls.
| Name | Model | Status |
|---|---|---|
| OpenAI | ||
| GPT-4.1 | gpt-4.1-2025-04-14 (default) |
✅ 🧠 |
| GPT-4o | gpt-4o-2024-08-06 (default) |
✅ 🧠 |
| GPT-4.5 Preview | gpt-4.5-preview-2025-02-27 (default) |
✅ 🧠 |
| ChatGPT o1 | o1-2024-12-17 (default) |
✅ 🧠 |
| ChatGPT o3-mini | o3-mini-2025-01-31 (default) |
✅ 🧠 |
| ChatGPT o3-mini-high | o3-mini-2025-01-31 (default) set reasoning_effort to high |
✅ 🧠 |
| ChatGPT 4o mini | gpt-4o-mini-2024-07-18 (default) |
✅ 🧠 |
| ChatGPT 4 | gpt-4-0613 (default) |
✅ 🧠 |
| Gemini | ||
| Gemini 2.5 Pro Preview | models/gemini-2.5-pro-preview-03-25 (default) |
✅ 🧠 |
| Gemini 2.5 Flash Preview | models/gemini-2.5-flash-preview-04-17 (default) |
✅ 🧠 |
| Gemini 2.0 Flash | models/gemini-2.0-flash (default) |
✅ 🧠 |
| Gemini 2.0 Flash | models/gemini-2.0-flash (default) |
✅ 🧠 |
| Gemini 2.0 Flash Lite | models/gemini-2.0-flash-lite (default) |
✅ 🧠 |
| Gemini 1.5 Flash | models/gemini-1.5-flash (default) |
✅ 🧠 |
Notes:
o3-mini-high
This model is simply o3-mini with reasoning_effort set to high.
Details: https://community.openai.com/t/is-03-mini-in-the-api-the-low-medium-or-high-version/1110423/2
Handling OpenAI Compatible Endpoints
Some providers offer additional endpoints are compatible with OpenAI, for example Google Gemini OpenAI Compatiblity. This is reflected in the YAML like so:
providers:
gemini:
id: gemini
api_specification: generativelanguage.googleapis.com/v1beta
base_url: https://generativelanguage.googleapis.com/v1beta/
additional_endpoints:
- api_specification: api.openai.com/v1 # Gemini has an OpenAI compatible endpoint...
base_url: https://generativelanguage.googleapis.com/v1beta/openai/