Available Models
This page lists all language models available for AI Agents, including supported providers and reasoning capabilities. Choose the best option for your use case based on performance, speed, and reasoning support.
Available Models List Copy link
We provide access to the following large language models:
|
Provider |
Model |
Reasoning |
|
OpenAI |
GPT-4.1 |
❌ |
|
OpenAI |
GPT-5 |
✅ |
|
OpenAI |
GPT-5 mini |
✅ |
|
OpenAI |
GPT-5 nano |
✅ |
|
OpenAI |
GPT-5.1 |
✅ |
|
OpenAI |
GPT-5.2 |
✅ |
|
OpenAI |
GPT-5.3 Codex |
✅ |
|
OpenAI |
GPT-5.4 |
✅ |
|
OpenAI |
GPT-5.4 Mini |
✅ |
|
OpenAI |
GPT-5.4 Nano |
✅ |
|
OpenAI |
GPT 5.5 |
✅ |
|
DeepSeek |
DeepSeek V3.2 |
❌ |
|
DeepSeek |
DeepSeek V3.2 |
✅ |
|
DeepSeek |
DeepSeek V4 Flash |
❌ |
|
DeepSeek |
DeepSeek V4 Flash Thinking |
✅ |
|
DeepSeek |
DeepSeek V4 Pro |
❌ |
|
DeepSeek |
DeepSeek V4 Pro Thinking |
✅ |
|
xAI |
Grok 3 |
✅ |
|
xAI |
Grok 4 |
❌ |
|
xAI |
Grok 4 Fast |
❌ |
|
xAI |
Grok 4 Fast |
✅ |
|
xAI |
Grok 4.1 Fast |
❌ |
|
xAI |
Grok 4.1 Fast |
✅ |
|
xAI |
Grok Code Fast |
✅ |
|
Anthropic |
Claude Haiku 3.5 |
❌ |
|
Anthropic |
Claude Fable 5 |
✅ |
|
Anthropic |
Claude Haiku 4.5 |
✅ |
|
Anthropic |
Claude Opus 4.1 |
✅ |
|
Anthropic |
Claude Opus 4.5 |
✅ |
|
Anthropic |
Claude Opus 4.6 |
✅ |
|
Anthropic |
Claude Opus 4.7 |
✅ |
|
Anthropic |
Claude Sonnet 4.0 |
✅ |
|
Anthropic |
Claude Sonnet 4.5 |
✅ |
|
Anthropic |
Claude Sonnet 4.6 |
✅ |
|
Google AI |
Gemini 2.5 Flash |
❌ |
|
Google AI |
Gemini 2.5 Flash Lite |
❌ |
|
Google AI |
Gemini 3 Flash Preview |
✅ |
|
Google AI |
Gemini 3.1 Flash Lite |
✅ |
|
Google AI |
Gemini 2.5 Pro |
✅ |
|
Google AI |
Gemini 3 Pro Preview |
✅ |
|
Google AI |
Gemini 3.1 Pro Preview |
✅ |
|
Qwen |
Qwen 3.5 Flash |
❌ |
|
Qwen |
Qwen 3.5 Flash |
✅ |
|
Qwen |
Qwen 3.5 Plus |
❌ |
|
Qwen |
Qwen 3.5 Plus |
✅ |
|
Qwen |
Qwen 3.6 Plus |
❌ |
|
Qwen |
Qwen 3.6 Plus |
✅ |
|
Qwen |
Qwen 3 Max |
❌ |
Reasoning Models Copy link
If a model displays a brain icon, it supports reasoning mode.
In this mode, the model generates intermediate reasoning steps before producing the final answer. It asks itself clarifying questions and answers them internally. This helps produce more accurate and well-structured responses, especially for complex tasks.
Each reasoning step requires additional input and output text, which increases token usage.
Reasoning mode cannot be disabled.