AI Model Tracker — OpenAI, Anthropic, Google, Mistral

AI Model Tracker returns current model IDs, context windows, input/output pricing, vision support, function-calling support, and cost tier classification across OpenAI, Anthropic, Google, Mistral, Cohere, Meta, and Groq — sourced from the LiteLLM model prices dataset. No API key required. $0.003/model.

The AI model landscape changes weekly. New models drop, pricing shifts, context windows expand. This actor gives you a structured, filterable snapshot of the entire LLM pricing universe — automatable, queryable, and up to date.

---

Why use AI Model Tracker?

1. LLM cost comparison — Before building a production API integration, pull all chat models and sort by input_cost_per_1m_tokens. Premium models cost 50x more than budget alternatives — make the decision with data.
2. New model release monitoring — Schedule weekly runs and compare the result set against last week's dataset. New model_id entries = newly released models. Never miss a release.
3. Capability-filtered model selection — Filter to supports_vision: true and minContextWindow: 128000 to find all multimodal long-context models across providers in one query.
4. AI cost dashboards — Power internal cost optimization dashboards with live pricing data instead of manually checking 7 provider docs.
5. Vendor benchmarking — Track how different providers price equivalent capability tiers (premium vs. standard vs. budget) over time.

---

How to use

1. Open the actor on Apify Store and click Try for free.
2. Set providers to the AI companies you want to track (empty = all 7 providers).
3. Set modesFilter to focus on a model type (e.g. ["chat"] for text generation models only).
4. Set minContextWindow to filter out short-context models.
5. Click Start. Returns structured model records.

---

Input

Field	Type	Default	Description
providers	string[]	all	AI providers to include (see list below)
modesFilter	string[]	all	Model types: chat, embedding, image, audio, completion
minContextWindow	integer	0	Only return models with at least this many tokens context

Supported providers

Value	Models
openai	GPT-4o, GPT-4 Turbo, o1, o3, GPT-3.5, …
anthropic	Claude 4.x, Claude 3.5/3 Opus/Sonnet/Haiku, …
google	Gemini 2.0, Gemini 1.5 Pro/Flash, …
mistral	Mistral Large, Mistral Small, Codestral, …
cohere	Command R+, Command R, …
meta	Llama 3.x variants
groq	Groq-hosted models

---

Output

{
  "model_id": "gpt-4o",
  "provider": "openai",
  "mode": "chat",
  "context_window_tokens": 128000,
  "max_output_tokens": 4096,
  "input_cost_per_1m_tokens": 5.0,
  "output_cost_per_1m_tokens": 15.0,
  "supports_vision": true,
  "supports_function_calling": true,
  "supports_audio_input": false,
  "cost_tier": "premium",
  "fetched_at": "2026-09-02T10:00:00Z"
}

Cost tier classification

Tier	Input cost per 1M tokens	Examples
budget	< $1.00	GPT-3.5, Haiku, Gemini Flash
standard	$1.00–$5.00	Sonnet, Gemini Pro, Mistral Large
premium	> $5.00	GPT-4o, Claude Opus, Gemini Ultra

---

Cost estimation

Pay-Per-Event: $0.003 per model returned.

Use case	Models	Estimated cost
All chat models (~200)	200	~$0.60/run
OpenAI + Anthropic only (~50)	50	~$0.15/run
Weekly new model check	200	~$0.60/week
Premium multimodal filter (~20)	20	~$0.06/run

---

Example queries

All chat models:

{ "modesFilter": ["chat"] }

OpenAI + Anthropic with 128K+ context:

{ "providers": ["openai","anthropic"], "minContextWindow": 128000 }

Find all vision-capable premium models (filter in code):

{ "modesFilter": ["chat"] }

Then filter results where supports_vision == true && cost_tier == "premium".

---

FAQ

How current is the pricing data? The LiteLLM model prices dataset is community-maintained and updated frequently. It typically lags official provider announcements by a few days. For production billing, always verify against the provider's official pricing page.

Does it include fine-tuned model pricing? The dataset includes some fine-tuned model pricing where available. Filter by model_id containing "ft:" or similar to identify fine-tuned entries.

Can I access non-default providers (DeepSeek, Grok, Azure)? Yes — add provider names like "deepseek", "xai", "azure" to the providers filter. These are available in the underlying dataset but filtered out by default for relevance.

What does mode: "embedding" mean? Embedding models convert text to vector representations. They're priced differently (no output cost) and have different context windows than chat models. Use modesFilter: ["embedding"] to pull only embedding model pricing.

---

Related actors

• Crypto News Sentiment Analyzer — Uses Claude (Anthropic API); this actor helps you choose which Claude model to use
• PyPI Package Analyzer — Tracks AI library downloads (anthropic, openai, transformers) to complement model tracking
• GitHub Repo Stats Tracker — Track AI provider GitHub repos (openai/openai-python, anthropics/anthropic-sdk-python)

Feedback

If this actor helps your AI cost research, a quick review helps others find it: Leave a review on Apify Store

---

Keywords: OpenAI model tracker, GPT-4 pricing, Claude pricing, AI model comparison, LLM cost tracker, AI API pricing, GPT model list, Gemini pricing, Anthropic models, AI model context window, tokens per dollar, LLM benchmark comparison, AI provider pricing, latest AI models, AI API cost calculator