Models

For high-volume, latency-sensitive tasks such as classification, extraction, and routing

GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work.

For long-running agentic coding and knowledge work

Our most efficient model for focused, high-volume tasks.

Built to power complex coding and agentic workflows.

Legacy GPT model for cheaper chat

SpaceXAI's frontier model for coding, agentic tasks, and knowledge work.

Coding and agent capabilities are improved across the board, with significantly more efficient thinking than K2.7 Code.

Our most capable model for the most demanding work.

Gemini 3.8 Flash is our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

For demanding reasoning and long-horizon agentic work

Gemini Omni Flash is a high-performance model for fast, conversational video generation and editing.

GLM-5.3 is Z.ai's latest flagship model, delivering comprehensive advancements in complex software engineering and agent capabilities.

Major Agent upgrades with strong production gains!

Gemini 3.7 Flash is the next iteration in the Gemini 3 series of highly-capable, natively multimodal, reasoning models.

SpaceXAI's frontier model for coding, agentic tasks, and knowledge work.

Opus 5 is designed to be used every day: it works more efficiently than other models.

Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing.

designed for frontier intelligence scenarios including long-horizon coding, knowledge work, and reasoning.

GPT-5.6 model optimized for cost-sensitive workloads

GPT-5.6 model that balances intelligence and cost

GPT-5.6 flagship model for complex professional work

SpaceXAI's intelligent coding model for agentic software, engineering, and workflow tasks.

Claude Sonnet 5 is built to be the most agentic Sonnet model yet.

Nano Banana 2 Lite is designed as the efficiency specialist of the image generation family

GLM-5.2 is a flagship model built for the era of long-horizon tasks.

Kimi K2.7 Code is Kimi’s dedicated coding model.

showing exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas.

Frontier multimodal coding model

Nano Banana Pro is a sophisticated reasoning-driven engine for professional-grade image editing and generation, offering studio-quality precision and advanced creative control.

It builds on Opus 4.7 with improvements across benchmarks, and is a more effective collaborator.

Nano Banana 2 provides high-quality image generation and conversational editing at a mainstream price point and low latency.

Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost.

Major Agent upgrades with strong production gains!

Your fast, efficient, and economical choice.

Supports both visual and text input, thinking and non-thinking modes, and dialogue and Agent tasks.

Opus 4.7 is a notable improvement on Opus 4.6 in advanced software engineering, with particular gains on the most difficult tasks.

Beginning the journey of recursive self-improvement

Our strongest mini model yet for coding, computer use, and subagents

Our cheapest GPT-5.4-class model for simple high-volume tasks

Grok 4.20 is a high-performance model with industry-leading speed and agentic tool calling capabilities.

Grok 4.20 is a high-performance model with industry-leading speed and agentic tool calling capabilities.

A more affordable model for coding and professional work.

Version of GPT-5.4 that produces smarter and more precise responses.

The most capable agentic coding model to date.

This endpoint is better at prioritizing your custom tools

Gemini 3.1 Pro Preview provides better thinking, improved token efficiency

It’s a full upgrade of the model’s skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.

The new Claude Opus 4.6 improves on its predecessor’s coding skills.

Previous flagship model for professional work with configurable reasoning effort

It’s also meaningfully better at everyday tasks like deep research and working with slides and spreadsheets.

The best model for coding and agentic tasks with configurable reasoning effort

The fastest model with near-frontier intelligence

Version of GPT-5 that produces smarter and more precise responses

Our best engine for high-velocity visual creation, offering state-of-the-art speed and efficiency.

Fastest, most cost-efficient version of GPT-5

Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort

Strong intelligence for cost sensitive, low latency, high volume workloads

Our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM

Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini

Reasoning model for complex tasks, succeeded by GPT-5

Smartest non-reasoning model

Fastest, most cost-efficient version of GPT-4.1

Smaller, faster version of GPT-4.1

A small model alternative to o3

Fast, affordable small model for focused tasks

Fast, intelligent, flexible GPT model

Fast, intelligent, flexible GPT model

An older high-intelligence GPT model

Legacy GPT model for cheaper chat

Most capable embedding model

Small embedding model

Previous full o-series reasoning model

An older high-intelligence GPT model

Older embedding model

High-Speed version of Kimi K2.7 Code model

Fast, reliable model with strong tool calling and instruction following capabilities.