New274+ blocks and 249+ tools are now fully documented

AI Models

Every LLM provider Zelaxy supports, what each model can do — tool calling, vision, structured output, and extended thinking — and how to pick one.

The Agent block (and Evaluator, Router, and Translate) can run on any supported provider. You pick a model from a dropdown; Zelaxy handles the provider's API contract, auth, and streaming. This page covers who's supported and what the models can do.

New models are added continuously. The list in the app's model dropdown is always the source of truth — this page describes the providers and capabilities rather than freezing an exact model count.

Supported providers

Every logo below is the same brand icon Zelaxy renders in its own model picker — not a placeholder.

Frontier labs

The flagship reasoning and multimodal model families.

OpenAI
OpenAI's models
Anthropic
Anthropic's Claude models
Google
Google's Gemini models
xAI
xAI's Grok models
DeepSeek
DeepSeek's chat models
Mistral
Mistral AI's chat and code models
Meta
Muse Spark via the Meta Model API

Fast inference

Purpose-built for high-throughput, low-latency serving of open and hosted models.

Groq
Groq's high-performance inference
Cerebras
Cerebras Cloud LLMs
Fireworks AI
Fireworks AI's fast open-source inference
Together AI
Together AI's open-source model inference
Baseten
Baseten's hosted open-source inference

Cloud-native

Run frontier models inside your own Azure, AWS, or GCP tenant for data residency and billing consolidation.

Azure OpenAI
Microsoft Azure OpenAI Service models
Azure Anthropic
Anthropic Claude models hosted on Microsoft Azure
AWS Bedrock
AWS Bedrock foundation models
Google Vertex AI
Google Gemini models on Vertex AI (GCP)

Open & self-hosted

Local, self-hosted, gateway, and additional thinking-capable providers.

Ollama
Local LLM models via Ollama
Ollama Cloud
Ollama's hosted inference for large models
vLLM
Self-hosted vLLM (OpenAI-compatible)
LiteLLM
Self-hosted LiteLLM proxy gateway
OpenRouter
Unified access to many providers
NVIDIA
NVIDIA NIM inference microservices
Z.ai
Z.ai's GLM models (OpenAI-compatible)
Mi
MiMo
Xiaomi's MiMo models (pay-as-you-go)
Mi
MiMo Token Plan
MiMo via credits-based subscription
Sakana AI
Sakana AI's Fugu models

To enable a provider, set its API key in your environment (e.g. OPENAI_API_KEY, ANTHROPIC_API_KEY, DEEPSEEK_API_KEY) — see Deployment.

Model capabilities

Not every model supports every feature. Zelaxy reads each model's capabilities and adapts the Agent block's UI accordingly — options that don't apply are hidden.

CapabilityWhat it meansWhere it shows up
Tool callingThe model can call connected tool blocks during reasoning.Connect any tool to the Agent as an agent tool.
Tool-usage controlYou can force, disallow, or auto-select tool use.Agent block → tool settings.
Structured outputThe model returns typed JSON matching a schema.Agent block → Response Format. Read the result from {{agent.output}}.
VisionThe model can read images.Pass image inputs; or use the Vision block.
Extended thinkingThe model exposes a real reasoning phase (Anthropic thinking, MiMo thinking:{type}, o-series effort).Agent block → Thinking toggle (shown only for models that support it).
Temperature rangeSome models accept 0–2, others a narrower range or none.Agent block → temperature slider adapts automatically.

Extended thinking

Thinking-capable models — including Claude (Sonnet/Opus/Fable), MiMo, and the OpenAI o-series — can spend explicit reasoning tokens before answering. When you select one, the Agent block shows a Thinking toggle. Turning it on trades latency and cost for deeper reasoning on hard tasks.

Extended thinking changes provider constraints under the hood — for example, Anthropic thinking forces temperature = 1 and is incompatible with forced tool choice. Zelaxy applies these rules for you, but it's why some options grey out when Thinking is on.

Choosing a model

  • Hard reasoning, planning, code → a frontier reasoning model with Thinking on (Claude Opus, GPT-5/o-series).
  • High volume, low latency → Groq, Cerebras, or a small fast model (GPT-5-nano, Claude Haiku).
  • Cost-sensitive → DeepSeek, Mistral, or open models via Ollama/vLLM.
  • Data residency / your cloud → Azure OpenAI, Azure Anthropic, Bedrock, or Vertex AI.
  • Structured extraction → any tool-calling model with Response Format enabled.