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

# Overview

> Specs, pricing, and capabilities for every supported model

Every model supported by Timbal with full specs, pricing, capability scores, and short descriptions. **Price** = per 1M tokens (input / output). All models support tool/function calling unless noted.

<CardGroup cols={3}>
  <Card title="Anthropic" icon="https://timbalusercontent.com/assets/claude_favicon.svg" href="/models/anthropic">
    Claude Fable 5, Opus 5, Sonnet 5, and Haiku
  </Card>

  <Card title="BytePlus" icon="https://timbalusercontent.com/assets/byteplus_favicon.svg" href="/models/byteplus">
    Seed 2.0 and Seed 1.8 models
  </Card>

  <Card title="Cerebras" icon="https://timbalusercontent.com/assets/cerebras_favicon.svg" href="/models/cerebras">
    Wafer-scale inference at world-record token speeds
  </Card>

  <Card title="Fireworks" icon="https://timbalusercontent.com/assets/fireworks_favicon.svg" href="/models/fireworks">
    Open-source models via Fireworks
  </Card>

  <Card title="Google" icon="https://timbalusercontent.com/assets/gemini_favicon.svg" href="/models/google">
    Gemini 3.6, 3.5, 3.1 and 2.5 series
  </Card>

  <Card title="Groq" icon="https://timbalusercontent.com/assets/groq_favicon.svg" href="/models/groq">
    Ultra-low latency via Groq LPU
  </Card>

  <Card title="Moonshot (Kimi)" icon="https://timbalusercontent.com/assets/moonshot_favicon.svg" href="/models/moonshot">
    Kimi K3 / K2.x via Moonshot's OpenAI-compatible API
  </Card>

  <Card title="OpenAI" icon="https://timbalusercontent.com/assets/openai_favicon.svg" href="/models/openai">
    GPT-5, GPT-4, and o-series reasoning models
  </Card>

  <Card title="SambaNova" icon="https://timbalusercontent.com/assets/sambanova_favicon.svg" href="/models/sambanova">
    High-throughput inference on custom RDU hardware
  </Card>

  <Card title="TogetherAI" icon="https://timbalusercontent.com/assets/together_favicon.svg" href="/models/togetherai">
    Open-source models via TogetherAI
  </Card>

  <Card title="xAI" icon="https://timbalusercontent.com/assets/grok_favicon.svg" href="/models/xai">
    Grok 4 and Grok 4 Fast
  </Card>

  <Card title="Xiaomi MiMo" icon="https://timbalusercontent.com/assets/xiaomi_favicon_rounded.svg" href="/models/xiaomi">
    MiMo V2 Pro, Omni, and Flash
  </Card>
</CardGroup>

## Scoring

Each model is rated on two axes using a **1-5 scale**:

* **Reasoning** — depth of analytical and chain-of-thought capability
* **Speed** — relative latency and throughput for its class

Scores are **relative within the full set of models on this page**, not within a single provider. A reasoning score of 5 means frontier-class reasoning (e.g. o3-pro, Claude Opus 4.7, GPT-5.5, Gemini 2.5 Pro). A speed score of 5 means the fastest tier (nano/mini/flash-lite models, or Groq-hosted inference).