Model database
Explore the AI models supported by EidoStack
Finding the right model starts with understanding the differences between the available options. This directory gives you a single place to review the models supported by EidoStack and identify the ones that are most relevant to your application.
Explore models from OpenAI, Anthropic, and Google, including estimated input and output pricing, context window size, and maximum output limits. Use the directory to narrow down your options, open individual model pages for more details, and identify which models are worth testing for your application.
Choosing an AI model is rarely about one metric. Cost, context capacity, output limits, and response quality can all affect how well a model fits a particular workflow. EidoStack gives you a structured starting point for evaluating these trade-offs before testing models with your own prompts and use cases.
OpenAI
36 models| Model | Provider | Input price / 1M tokens | Output price / 1M tokens | Context window | Max output tokens |
|---|---|---|---|---|---|
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | 1,050,000 tokens | 128,000 |
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | 1,050,000 tokens | 128,000 |
| GPT-6 Sol | OpenAI | $2.00 | $10.00 | 1,050,000 tokens | 128,000 |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | 1,050,000 tokens | 128,000 |
| GPT-5.6 Sol | OpenAI | $5.00 | $30.00 | 1,050,000 tokens | 128,000 |
| GPT-5.6 Terra | OpenAI | $2.50 | $15.00 | 1,050,000 tokens | 128,000 |
| GPT-5.6 Luna | OpenAI | $1.00 | $6.00 | 1,050,000 tokens | 128,000 |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | 1,050,000 tokens | — |
| GPT-5.5 Pro | OpenAI | $30.00 | $180.00 | 1,050,000 tokens | — |
| GPT-5.4 | OpenAI | $2.50 | $15.00 | 1,050,000 tokens | — |
| GPT-5.4 Pro | OpenAI | $30.00 | $180.00 | 1,050,000 tokens | — |
| GPT-5.4 Mini | OpenAI | $0.75 | $4.50 | 400,000 tokens | — |
| GPT-5.4 Nano | OpenAI | $0.20 | $1.25 | 400,000 tokens | — |
| GPT-5.3 Chat Latest | OpenAI | $1.75 | $14.00 | 128,000 tokens | — |
| GPT-5.3 Codex | OpenAI | $1.75 | $14.00 | 400,000 tokens | — |
| GPT-5.2 | OpenAI | $1.75 | $14.00 | 400,000 tokens | — |
| GPT-5.2 Pro | OpenAI | $21.00 | $168.00 | 400,000 tokens | — |
| GPT-5.1 | OpenAI | $1.25 | $10.00 | 400,000 tokens | — |
| GPT-5 | OpenAI | $1.25 | $10.00 | 400,000 tokens | — |
| GPT-5 (2025-08-07) | OpenAI | $1.25 | $10.00 | 400,000 tokens | — |
| GPT-5 Pro | OpenAI | $15.00 | $120.00 | 400,000 tokens | — |
| GPT-5 Mini | OpenAI | $0.25 | $2.00 | 400,000 tokens | — |
| GPT-5 Nano | OpenAI | $0.05 | $0.40 | 400,000 tokens | — |
| GPT-4.1 | OpenAI | $2.00 | $8.00 | 1,047,576 tokens | — |
| GPT-4.1 (2025-04-14) | OpenAI | $2.00 | $8.00 | 1,047,576 tokens | — |
| GPT-4.1 Mini | OpenAI | $0.40 | $1.60 | 1,047,576 tokens | — |
| GPT-4.1 Nano | OpenAI | $0.10 | $0.40 | 1,047,576 tokens | — |
| GPT-4o | OpenAI | $2.50 | $10.00 | 128,000 tokens | — |
| GPT-4o (2024-11-20) | OpenAI | $2.50 | $10.00 | 128,000 tokens | — |
| GPT-4o (2024-05-13) | OpenAI | $5.00 | $15.00 | 128,000 tokens | — |
| GPT-4o Mini | OpenAI | $0.15 | $0.60 | 128,000 tokens | — |
| GPT-4o Mini Search Preview | OpenAI | $0.15 | $0.60 | 128,000 tokens | — |
| GPT-4o Search Preview | OpenAI | $2.50 | $10.00 | 128,000 tokens | — |
| GPT-4 Turbo | OpenAI | $10.00 | $30.00 | 128,000 tokens | — |
| GPT-4 | OpenAI | $30.00 | $60.00 | 8,192 tokens | — |
| GPT-3.5 Turbo | OpenAI | $0.50 | $1.50 | 4,096 tokens | — |
Anthropic
13 models| Model | Provider | Input price / 1M tokens | Output price / 1M tokens | Context window | Max output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | 1,000,000 tokens | 128,000 |
| Claude Fable 5 | Anthropic | $10.00 | $50.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 4.8 | Anthropic | $5.00 | $25.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 4.6 | Anthropic | $5.00 | $25.00 | 1,000,000 tokens | 128,000 |
| Claude Opus 4.5 | Anthropic | $5.00 | $25.00 | 200,000 tokens | 64,000 |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | 1,000,000 tokens | 128,000 |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | 1,000,000 tokens | 128,000 |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | 1,000,000 tokens | 128,000 |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | 200,000 tokens | 64,000 |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200,000 tokens | 64,000 |
| Model | Provider | Input price / 1M tokens | Output price / 1M tokens | Context window | Max output tokens |
|---|---|---|---|---|---|
| Gemini 3.8 Flash | $0.75 | $3.75 | 1,048,576 tokens | 65,536 | |
| Gemini 3.7 Flash | $0.75 | $3.75 | 1,048,576 tokens | 65,536 | |
| Gemini 3.6 Flash | $1.50 | $7.50 | 1,048,576 tokens | 65,536 | |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1,048,576 tokens | — | |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1,048,576 tokens | 65,536 | |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | 1,048,576 tokens | 65,536 | |
| Gemini 3 Flash Preview | $0.50 | $3.00 | 1,048,576 tokens | — | |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | 1,048,576 tokens | — | |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1,048,576 tokens | — | |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1,048,576 tokens | — | |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1,048,576 tokens | — |
Common Questions
What is the EidoStack AI Models database?
The EidoStack AI Models database is a directory of AI models available for evaluation in EidoStack. It brings together useful model information such as provider, estimated input and output pricing, context window size, and maximum output limits so you can review different options in one place.
Which AI providers are included?
EidoStack currently includes supported models from OpenAI, Anthropic, and Google. The models directory groups models by provider and lets you filter the catalog or search for a specific model by name.
How can I compare AI models?
Start by comparing model specifications such as pricing, context window, and output limits in the models directory. You can then use EidoStack to test models with your own prompts and compare their responses, token usage, and estimated cost under the same workflow.
What do input and output prices mean?
Input price is the estimated cost of the tokens you send to a model, including prompts and context. Output price is the estimated cost of the tokens generated by the model. EidoStack displays both values per one million tokens where pricing information is available.
What is an AI model context window?
The context window is the maximum amount of information a model can process within a request, typically measured in tokens. It can include your prompt, conversation history, system instructions, retrieved context, and other input sent to the model.
What does maximum output mean?
Maximum output indicates how many tokens a model can generate in a single response. A larger output limit can be useful for tasks that require long-form content, large code changes, detailed analysis, or structured data generation.
Is the cheapest AI model always the best choice?
Not necessarily. Token price is only one factor when selecting a model. The right choice also depends on response quality, context requirements, output limits, latency, and how the model performs on your specific prompts and application workflow.
Can I test these models in EidoStack?
Yes. EidoStack is designed to help you evaluate AI models using your own prompts and workflows. You can test supported models, compare responses side by side, and analyze token usage and estimated cost before deciding which model is a better fit for your application.
How should I choose an AI model for my application?
Start with the requirements of your use case: expected context size, response length, cost constraints, and required output quality. Shortlist models using the directory, then test the candidates with representative prompts from your application. Comparing models under the same conditions gives you more useful information than choosing based on specifications alone.