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

# Chatbot Models

A complete reference for all chatbot models available in Qolaba — context window, input and output credit costs, and best use cases organized by provider

Qolaba's Chatbot gives you access to 24 large language models across six providers — all from a single interface. Each model has a different context window, credit cost, and area of strength. Use this page as a reference when selecting a model for a specific task.

***

### How to Read This Page

<table><thead><tr><th width="229.64453125">Column</th><th>What It Means</th></tr></thead><tbody><tr><td><strong>Context Window</strong></td><td>Maximum tokens the model can process in a single request — includes your prompt, conversation history, uploaded files, and the model's response. See <a href="https://docs.qolaba.ai/chatbot/model-selection/model-information-panel.md">Model Information Panel →</a> for a detailed explanation of how context windows work.</td></tr><tr><td><strong>Input Credits / 1K tokens</strong></td><td>Credits consumed per 1,000 input tokens — your prompt, files, conversation history, and system instructions</td></tr><tr><td><strong>Output Credits / 1K tokens</strong></td><td>Credits consumed per 1,000 output tokens — the model's generated response, including thinking tokens if Thinking Depth is enabled</td></tr></tbody></table>

{% hint style="info" %}
Models marked with ⭐ are available on **paid plans only**.
{% endhint %}

***

### Gemini Models

*Google*

Gemini models are Google's family of large language models — strong across long-context tasks, multimodal inputs, and general-purpose generation. Every Gemini model has a 1M token context window, which makes them well-suited for large document analysis, extended research sessions, and long conversations.

| Model                     | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                              |
| ------------------------- | -------------- | ------------------ | ------------------- | --------------------------------------------------------------------- |
| **Gemini 3.1 Flash Lite** | 1M             | 0.065              | 0.39                | Lowest-cost Gemini — high-volume, low-latency tasks and quick queries |
| **Gemini 3.5 Flash-Lite** | 1M             | 0.078              | 0.65                | High-volume automation — search, document processing, translation     |
| **Gemini 4 Hydrogen**     | 1M             | 0.39               | 1.95                | Everyday Gemini 4 model — coding and agentic workflows                |
| **Gemini 3.8 Flash** ⭐    | 1M             | 0.39               | 1.95                | Long-horizon coding, autonomous agents, complex enterprise workflows  |
| **Gemini 4 Neon** ⭐       | 1M             | 0.78               | 3.90                | Newest Gemini 4 model — multimodal input, thinking up to extra-high   |
| **Gemini 4 Argon** ⭐      | 1M             | 1.04               | 5.20                | Strong reasoning at lower latency                                     |
| **Gemini 4 Carbon** ⭐     | 1M             | 1.04               | 5.20                | Gemini 4 flagship — the hardest reasoning tasks                       |

***

### Claude Models

*Anthropic*

Claude models are Anthropic's family of large language models — known for strong instruction following, nuanced writing quality, and reliable performance on long-form content. Every Claude model has a 1M token context window, making them well-suited for detailed documents, complex briefs, and extended reasoning tasks.

| Model                   | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                                              |
| ----------------------- | -------------- | ------------------ | ------------------- | ------------------------------------------------------------------------------------- |
| **Claude Haiku 5.5**    | 1M             | 0.026              | 0.13                | Fastest, lowest-cost Claude — high-volume and latency-sensitive tasks                 |
| **Claude Sonnet 5.5** ⭐ | 1M             | 0.52               | 2.60                | Balanced quality and speed — everyday coding, writing, and analysis                   |
| **Claude Opus 5.5** ⭐   | 1M             | 1.04               | 5.20                | Recommended starting point for serious coding and knowledge work — near-Fable quality |
| **Claude Fable 5.2** ⭐  | 1M             | 2.08               | 10.40               | Most capable Claude — the hardest coding, research, and agentic work                  |

***

### OpenAI Models

*OpenAI*

OpenAI's GPT-6 family spans fast, low-cost models for everyday tasks to frontier models for the hardest work. All four offer configurable reasoning effort, strong prompt comprehension, reliable structured output, and a 1M token context window.

| Model               | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                                      |
| ------------------- | -------------- | ------------------ | ------------------- | ----------------------------------------------------------------------------- |
| **GPT-6 Luna**      | 1M             | 0.026              | 0.13                | Fastest, lowest-cost GPT — high-volume tasks, quick answers                   |
| **GPT-6.1 Terra** ⭐ | 1M             | 0.26               | 1.30                | Cost-efficient reasoning, coding, and agentic tasks                           |
| **GPT-6.2 Sol** ⭐   | 1M             | 0.52               | 2.60                | Versatile everyday model — close to Astra on coding at a fraction of the cost |
| **GPT-6.2 Astra** ⭐ | 1M             | 2.08               | 10.40               | OpenAI's frontier model — the hardest professional projects                   |

***

### DeepSeek Models

*DeepSeek*

DeepSeek models deliver strong technical performance — particularly for coding, mathematical reasoning, and analytical tasks — at highly competitive credit costs. Well-suited for developer workflows and cost-sensitive high-volume use cases.

| Model                   | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                               |
| ----------------------- | -------------- | ------------------ | ------------------- | ---------------------------------------------------------------------- |
| **DeepSeek V4 Flash**   | 1M             | 0.0234             | 0.0468              | Lowest-cost model in Qolaba — fast reasoning and coding at high volume |
| **DeepSeek V4.1 Flash** | 1M             | 0.078              | 0.312               | Fast and affordable, with native vision for image inputs               |
| **DeepSeek V4 Pro** ⭐   | 1M             | 0.3432             | 1.0296              | Full-codebase analysis, multi-step automation, large-scale synthesis   |

***

### Grok Models

*xAI*

Grok models are xAI's family of large language models — built for fast, accurate responses with strong general capability and configurable reasoning effort.

| Model          | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                        |
| -------------- | -------------- | ------------------ | ------------------- | --------------------------------------------------------------- |
| **Grok 4.3**   | 1M             | 0.325              | 0.65                | Agentic workflows, instruction following, high factual accuracy |
| **Grok 4.7** ⭐ | 500K           | 0.52               | 1.56                | xAI's smartest model — coding and knowledge work                |

***

### Perplexity Models

*Sonar*

Perplexity's Sonar models are purpose-built for web-grounded responses — all models have built-in internet search, delivering answers backed by live, up-to-date sources rather than training data alone. Best for research, fact-checking, competitive intelligence, and any query where current information matters.

{% hint style="info" %}
Sonar models also use **1.3 credits per web search request** the model makes, on top of their token credits.
{% endhint %}

| Model                     | Context Window | Input Credits / 1K | Output Credits / 1K | Best For                                                                                         |
| ------------------------- | -------------- | ------------------ | ------------------- | ------------------------------------------------------------------------------------------------ |
| **Sonar**                 | 127K           | 0.26               | 0.26                | Fast web-grounded responses — general research, current events, quick fact-checking              |
| **Sonar Pro** ⭐           | 200K           | 0.78               | 3.90                | Higher quality web-grounded responses — detailed research, in-depth analysis with live sources   |
| **Sonar Reasoning Pro** ⭐ | 200K           | 0.52               | 2.08                | Web-grounded reasoning — research tasks requiring logical analysis of live information           |
| **Sonar Deep Research** ⭐ | 128K           | 0.52               | 2.08                | Deep, multi-source research — comprehensive reports, competitive analysis, thorough fact-finding |

***

### Choosing the Right Model

With 24 models available, here is a practical starting point for common use cases:

| Use Case                              | Recommended Model                                 | Reason                                                |
| ------------------------------------- | ------------------------------------------------- | ----------------------------------------------------- |
| **Everyday tasks and drafting**       | Gemini 4 Hydrogen or GPT-6 Luna                   | Low cost, reliable quality, available on every plan   |
| **Professional writing and analysis** | Claude Sonnet 5.5 or GPT-6.2 Sol                  | Strong writing quality and instruction following      |
| **Coding and agentic work**           | Claude Opus 5.5 or Gemini 3.8 Flash               | Built for long, multi-step coding and agent workflows |
| **Complex reasoning**                 | Gemini 4 Carbon or Gemini 4 Argon                 | Gemini 4's strongest reasoning models                 |
| **Premium quality — best output**     | Claude Fable 5.2 or GPT-6.2 Astra                 | Flagship models for the hardest work                  |
| **Research with live web data**       | Sonar Pro or Sonar Deep Research                  | Built-in web search for current, sourced answers      |
| **Long document analysis**            | Gemini 4 Hydrogen or Claude Sonnet 5.5            | 1M token context window                               |
| **High-volume, cost-sensitive tasks** | DeepSeek V4 Flash, Claude Haiku 5.5 or GPT-6 Luna | Lowest credit cost per token                          |
