> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fortapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Access dozens of frontier AI models from leading providers with one API key

FortAPI aggregates models from major AI providers behind a single endpoint. One API key — dozens of models, no separate accounts at each vendor.

## Major providers

<CardGroup cols={2}>
  <Card title="OpenAI" icon="circle-nodes">
    GPT-5, GPT-5-mini, the o-series and the rest of the family.
  </Card>

  <Card title="Anthropic Claude" icon="brain">
    Claude Sonnet, Claude Haiku, Claude Opus.
  </Card>

  <Card title="Google Gemini" icon="atom">
    Gemini Flash, Gemini Pro and experimental models.
  </Card>

  <Card title="xAI Grok" icon="rocket">
    Grok — models from xAI.
  </Card>

  <Card title="DeepSeek" icon="microchip">
    DeepSeek — strong reasoning at affordable prices.
  </Card>

  <Card title="And more" icon="ellipsis">
    Qwen, Yi, Mistral, Llama and new models as they ship.
  </Card>
</CardGroup>

## Model capabilities

The catalog covers different use cases:

* **Chat & text**: classic LLMs for conversation, code, analysis.
* **Multimodal (vision)**: models that understand images.
* **Tool use / function calling**: invoke external tools from model output.
* **Reasoning**: chain-of-thought models (o4-mini, DeepSeek R1, Claude thinking).
* **Embeddings**: vector representations for search and RAG.
* **Audio**: speech recognition and synthesis (where supported).

## Why FortAPI

<CardGroup cols={2}>
  <Card title="No VPN required" icon="shield-check">
    Direct access to every model — calls are made through our infrastructure.
  </Card>

  <Card title="One API key" icon="key">
    No separate accounts at OpenAI, Anthropic and others. One key — every frontier model worldwide.
  </Card>

  <Card title="Discounted vendor pricing" icon="tag">
    Billed per 1M tokens at a discount off each provider's official site price. No hidden markup.
  </Card>

  <Card title="Low latency" icon="bolt-lightning">
    Optimized request routing for fast response times.
  </Card>
</CardGroup>

## Full catalog and pricing

The list of available models, current per-token prices and supported capabilities lives on the **Pricing** page on the main site at [www.fortapi.com](https://www.fortapi.com).

## Choosing a model

* **Simple tasks** (classification, short answers): `gpt-5-mini`, `gemini-flash`, `claude-haiku` — most cost-efficient.
* **Complex tasks** (long-form analysis, coding, reasoning): `gpt-5`, `claude-sonnet`, `gemini-pro`.
* **Reasoning** (math, logic, multi-step thinking): `o4-mini`, `deepseek-r1`, `claude-sonnet` (with `thinking`).
* **Vision** (images): `gpt-5`, `claude-sonnet`, `gemini-flash` — all support vision.

See [Quickstart](/en/quickstart) for call examples and [API Reference](/en/api-reference) for OpenAI vs Claude protocol details.