AI Language Model APIs

Latest version of GPT-4 with extended context window, enhanced reasoning capabilities, and improved

o4-mini is our latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.

The most powerful reasoning model of OpenAI

A small model alternative to o3 - OpenAI

o1 - Previous full o-series reasoning model

A small model alternative to o1

o1-pro Version of o1 with more compute for better responses

GPT-4.1 Flagship GPT model for complex tasks

GPT-4o Fast, intelligent, flexible GPT model

GPT-4o Audio GPT-4o models capable of audio inputs and outputs

ChatGPT-4o GPT-4o model used in ChatGPT

GPT-4.1 mini Balanced for intelligence, speed, and cost

GPT-4.1 nano Fastest, most cost-effective GPT-4.1 model

GPT-4o mini Fast, affordable small model for focused tasks

GPT-4o mini Audio Smaller model capable of audio inputs and outputs

GPT-4o Realtime Model capable of realtime text and audio inputs and outputs

GPT-4o mini Realtime Smaller realtime model for text and audio inputs and outputs

GPT Image 1 State-of-the-art image generation model

DALL·E 3 Previous generation image generation model

DALL·E 2 Our first image generation model

GPT-4o mini TTS Text-to-speech model powered by GPT-4o mini

TTS-1 Text-to-speech model optimized for speed

TTS-1 HD Text-to-speech model optimized for quality

GPT-4o Transcribe Speech-to-text model powered by GPT-4o

GPT-4o mini Transcribe Speech-to-text model powered by GPT-4o mini

Whisper General-purpose speech recognition model

GPT-4o Search Preview GPT model for web search in Chat Completions

GPT-4o mini Search Preview Fast, affordable small model for web search

computer-use-preview Specialized model for computer use tool

codex-mini-latest Fast reasoning model optimized for the Codex CLI

text-embedding-3-small Small embedding model

text-embedding-3-large Most capable embedding model

text-embedding-ada-002 Older embedding model

GPT-4 An older high-intelligence GPT model

GPT-3.5 Turbo Legacy GPT model for cheaper chat and non-chat tasks

Gemini 2.5 Pro is Google's state-of-the-art thinking model with maximum response accuracy and enhanced reasoning capabilities for complex problems.

Gemini 2.5 Flash is Google's best model in terms of price-performance, offering well-rounded capabilities with adaptive thinking.

Gemini 2.0 Flash is Google's newest multimodal model with next generation features and improved capabilities, built to power agentic experiences.

Gemini 2.0 Flash-Lite is a lightweight version of Gemini 2.0 Flash optimized for cost efficiency and low latency.

Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks with excellent performance.

Gemini 1.5 Flash-8B is a smaller model designed for high volume and lower intelligence tasks with cost efficiency.

Gemini 1.5 Pro is a mid-size multimodal model optimized for complex reasoning tasks requiring more intelligence, with exceptional long-context capabilities.

Imagen 3 is Google's highest quality text-to-image model, capable of generating images with superior detail, richer lighting and fewer distracting artifacts.

Veo 2 is Google's high quality text- and image-to-video model, capable of generating detailed videos that capture artistic nuance from prompts.

Gemini 2.5 Flash Native Audio provides interactive and unstructured conversational experiences with high quality, natural conversational audio outputs, available with or without thinking capabilities.

Gemini 2.5 Flash Preview TTS is Google's price-performant text-to-speech model, delivering high control and transparency for structured workflows.

Gemini 2.5 Pro Preview TTS is Google's most powerful text-to-speech model, delivering high control and transparency for structured workflows.

Gemini 2.0 Flash Preview Image Generation delivers improved image generation features, including generating and editing images conversationally.

Gemini 2.0 Flash Live enables low-latency bidirectional voice and video interactions with Gemini through the Live API.

Claude Sonnet 4 balances impressive performance for coding with the right speed and cost for high-volume use cases.

Claude Opus 4 is Anthropic's most intelligent model and is state-of-the-art for coding and agent capabilities, especially agentic search.

Claude 3.7 Sonnet is Anthropic's most intelligent model to date and the first Claude model to offer extended thinking—the ability to solve complex problems with careful, step-by-step reasoning.

Claude 3.5 Haiku is Anthropic's fastest, most compact model for near-instant responsiveness.

Claude 3.5 Sonnet v2 is an upgraded version of Anthropic's Claude 3.5 Sonnet model, now state-of-the-art for a variety of tasks including real-world software engineering, agentic capabilities and computer use.

Claude 3.5 Sonnet raises the industry bar for intelligence, outperforming competitor models

Claude 3 Haiku is Anthropic's fastest, most compact model designed for near-instant responsiveness.

Grok-3 is xAI's flagship large language model designed for enterprise use cases with deep domain knowledge across finance, healthcare, law, and science.

Grok-3-Fast is the high-speed variant of Grok-3, offering identical quality with significantly reduced latency for time-sensitive applications.

Grok-3-Mini is a lightweight reasoning model that thinks before responding, featuring accessible raw thinking traces for transparency in logic-based tasks.

Grok-3-Mini-Fast is the high-speed variant of Grok-3-Mini, offering the same lightweight reasoning capabilities with enhanced response speed for time-critical applications.

Grok-2-Vision is xAI's multimodal model capable of understanding both text and images, designed for comprehensive visual analysis and reasoning tasks.

Grok-2-Image is xAI's specialized image generation model, capable of creating high-quality images from text descriptions.

Grok-2 is xAI's previous generation flagship text model, offering strong performance across a wide range of language understanding and generation tasks.

DeepSeek-R1 (deepseek-reasoner) is an advanced reasoning-focused large language model designed specifically for complex problem-solving with explicit chain-of-thought capabilities.

DeepSeek-V3 (deepseek-chat) is a powerful large language model developed by DeepSeek AI, designed for high-quality conversational AI applications with strong reasoning capabilities.