Overview - Timbal

Every model supported by Timbal with full specs, pricing, capability scores, and short descriptions. Price = per 1M tokens (input / output) at the provider’s standard short-context tier. Models with a long-context surcharge (OpenAI >272K, xAI >200K, BytePlus >128K input tokens) reprice the whole request; Timbal reports those requests under <unit>_long_context usage keys so they can be billed at the higher rate — see the OpenAI page. All models support tool/function calling unless noted.

Anthropic

Claude Fable 5.1, Opus 5, Sonnet 5, and Haiku

BytePlus

Seed 2.0 and Seed 1.8 models

Cerebras

Wafer-scale inference at world-record token speeds

Fireworks

Open-source models via Fireworks

Google

Gemini 3.6, 3.5, 3.1 and 2.5 series

Groq

Ultra-low latency via Groq LPU

Moonshot (Kimi)

Kimi K3 / K2.x via Moonshot’s OpenAI-compatible API

OpenAI

GPT-6 Astra, GPT-5, GPT-4, and o-series reasoning models

SambaNova

High-throughput inference on custom RDU hardware

TogetherAI

Open-source models via TogetherAI

xAI

Grok 4.6, Grok 4.5, and Grok 4.3

Xiaomi MiMo

MiMo V2 Pro, Omni, and Flash

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. GPT-6 Astra, Claude Fable 5.1, o3-pro, 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).