> For the complete documentation index, see [llms.txt](https://docs.flora.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flora.ai/models/text-models.md).

# Text Models

Here are all the text models currently available in FLORA.

<table><thead><tr><th width="220">Model</th><th width="120">Est. time (s)</th><th>Description</th><th>Best for</th></tr></thead><tbody><tr><td><strong>Claude Fable 5</strong></td><td>25</td><td>Anthropic's model capable of the most demanding reasoning and long-horizon agentic work.</td><td>Anthropic's model capable of the most demanding reasoning and long-horizon agentic work.</td></tr><tr><td><strong>Claude Fable 5.1</strong></td><td>25</td><td>Anthropic's most capable model for demanding reasoning and long-horizon agentic work.</td><td>Anthropic's most capable model for demanding reasoning and long-horizon agentic work.</td></tr><tr><td><strong>Claude Haiku 5.5</strong></td><td>8</td><td>Anthropic's fastest, lowest-cost model for high-volume work.</td><td>Anthropic's fastest, lowest-cost model for high-volume work.</td></tr><tr><td><strong>Claude Opus 4.5</strong></td><td>25</td><td>Combines maximum capability with practical performance.</td><td>In-depth domain expertise, nuanced dialogue, legal or policy analysis, and strategic decision support.</td></tr><tr><td><strong>Claude Opus 4.6</strong></td><td>8</td><td>Anthropic's frontier model, supports adaptive thinking.</td><td>Anthropic's frontier model, supports adaptive thinking.</td></tr><tr><td><strong>Claude Opus 4.7</strong></td><td>25</td><td>Flagship model by Anthropic that handles complex, long-running tasks.</td><td>Most advanced Anthropic reasoning, complex analysis, and highest-fidelity outputs.</td></tr><tr><td><strong>Claude Opus 4.8</strong></td><td>25</td><td>Anthropic's most capable model for complex reasoning.</td><td>Anthropic's most capable model for complex reasoning.</td></tr><tr><td><strong>Claude Opus 5</strong></td><td>25</td><td>Anthropic's most capable model for complex reasoning.</td><td>Anthropic's most capable model for complex reasoning.</td></tr><tr><td><strong>Claude Opus 5.5</strong></td><td>25</td><td>Anthropic's most capable Opus model for complex reasoning.</td><td>Anthropic's most capable Opus model for complex reasoning.</td></tr><tr><td><strong>Claude Sonnet 4.5</strong></td><td>25</td><td>Balanced speed and intelligence.</td><td>Balanced performance, creative writing, code generation, and versatile task handling.</td></tr><tr><td><strong>Claude Sonnet 4.6</strong></td><td>8</td><td>State-of-the-art results at fast speeds.</td><td>Balanced performance, creative writing, code generation, and versatile task handling.</td></tr><tr><td><strong>Claude Sonnet 5</strong></td><td>35</td><td>State-of-the-art results at fast speeds.</td><td>State-of-the-art results at fast speeds.</td></tr><tr><td><strong>Gemini 2.5 Pro</strong></td><td>30</td><td>Google's best for complex reasoning.</td><td>Enterprise-scale analytics, multimodal Q&#x26;A, detailed data synthesis, and robust safety-critical tasks.</td></tr><tr><td><strong>Gemini 3 Flash</strong></td><td>25</td><td>Transcribe audio files with reasoning.</td><td>Instant summarization, real-time assistance, mobile-first interactions, and search tasks.</td></tr><tr><td><strong>Gemini 3.1 Pro</strong></td><td>45</td><td>Google's latest and most capable reasoning model.</td><td>Advanced reasoning, complex analysis, and Google's most capable language model.</td></tr><tr><td><strong>Gemini 3.5 Flash-Lite</strong></td><td>4</td><td>Google's fastest, most cost-effective 3.5-class model.</td><td>Google's fastest, most cost-effective 3.5-class model.</td></tr><tr><td><strong>Gemini 4 Argon</strong></td><td>8</td><td>Google's frontier reasoning model for long-horizon coding, analysis and multimodal work.</td><td>Google's frontier reasoning model for long-horizon coding, analysis and multimodal work.</td></tr><tr><td><strong>Gemini Flash 3.6</strong></td><td>6</td><td>Efficiency-focused model, tuned multimodal tasks at a lower token cost than 3.5 Flash</td><td>Efficiency-focused model, tuned multimodal tasks at a lower token cost than 3.5 Flash</td></tr><tr><td><strong>Gemini Flash 3.7</strong></td><td>6</td><td>Coding and agent-tuned multimodal model, successor to Flash 3.6.</td><td>Coding and agent-tuned multimodal model, successor to Flash 3.6.</td></tr><tr><td><strong>Gemini Flash 3.8</strong></td><td>6</td><td>Agentic and software-engineering-tuned multimodal model, successor to Flash 3.7.</td><td>Agentic and software-engineering-tuned multimodal model, successor to Flash 3.7.</td></tr><tr><td><strong>GPT 4o Mini</strong></td><td>20</td><td>Fast and affordable for simple tasks.</td><td>Quick drafts, instant summarization, lightweight chatbots, and real-time user feedback loops.</td></tr><tr><td><strong>GPT-5</strong></td><td>40</td><td>Advanced reasoning with deep thinking.</td><td>Advanced reasoning, long-context analysis, high-precision code generation, and complex multi-step problem-solving.</td></tr><tr><td><strong>GPT-5.1</strong></td><td>30</td><td>OpenAI's advanced reasoning model.</td><td>Enhanced reasoning, complex analysis, and multi-step problem-solving with improved accuracy.</td></tr><tr><td><strong>GPT-5.2</strong></td><td>35</td><td>OpenAI’s model marking significant improvements in general intelligence.</td><td>Cutting-edge reasoning, highest accuracy, and most capable OpenAI model.</td></tr><tr><td><strong>GPT-5.4</strong></td><td>35</td><td>Versatile text model with advances in reasoning.</td><td>State-of-the-art reasoning, maximum accuracy, and OpenAI's flagship model.</td></tr><tr><td><strong>GPT-5.5</strong></td><td>24</td><td>Frontier model suitable for complex professional work.</td><td>Frontier model suitable for complex professional work.</td></tr><tr><td><strong>GPT-6 Astra</strong></td><td>30</td><td>OpenAI's flagship reasoning model for complex creative and professional work.</td><td>OpenAI's flagship reasoning model for complex creative and professional work.</td></tr><tr><td><strong>GPT-6 Luna</strong></td><td>10</td><td>OpenAI's fastest, lowest-cost GPT-6 model for summarizing, extracting, and quick answers.</td><td>OpenAI's fastest, lowest-cost GPT-6 model for summarizing, extracting, and quick answers.</td></tr><tr><td><strong>GPT-6 Sol</strong></td><td>20</td><td>OpenAI's efficient GPT-6 reasoning model for coding and complex everyday work.</td><td>OpenAI's efficient GPT-6 reasoning model for coding and complex everyday work.</td></tr><tr><td><strong>GPT-6.1 Sol</strong></td><td>20</td><td>OpenAI's efficient GPT-6.1 reasoning model, close to GPT-6 Astra on complex work at a fifth of the price.</td><td>OpenAI's efficient GPT-6.1 reasoning model, close to GPT-6 Astra on complex work at a fifth of the price.</td></tr><tr><td><strong>o3 Deep Research</strong></td><td>600</td><td>Use multi-step analysis with web search support.</td><td>In-depth research, comprehensive analysis, multi-source synthesis, and complex investigation tasks.</td></tr><tr><td><strong>Recraft Style Creator</strong></td><td>5</td><td>Creates a reusable Recraft style from reference images.</td><td>Creates a reusable Recraft style from reference images.</td></tr><tr><td><strong>Recraft Vector Style Creator</strong></td><td>5</td><td>Creates a reusable Recraft vector style from reference images.</td><td>Creates a reusable Recraft vector style from reference images.</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.flora.ai/models/text-models.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.