Models

Codex GPT for repository edits, code review, and practical software agents

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Thinking Kimi model for slower research passes, planning, and hard technical questions

High-effort o3 tier for difficult technical reasoning and careful answers

Open MiMo model for multimodal coding agents and long-context automation

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

Small GPT-5 for responsive agents, coding help, and everyday automation

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

StepFun flash lane for quick multimodal reasoning and coding assistance

Open Gemma instruction model for efficient chat and self-hosted deployments

Fast o-series model for compact reasoning, coding, and tool use

Google's proven reasoning model for coding, math, and multimodal analysis

Low-latency Gemini model for high-volume multimodal and agent workloads

Fast Gemini workhorse for multimodal apps where latency and price matter

O-series reasoning model for hard analysis, math, coding, and planning

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

DeepSeek chat model for instruction following, coding, and analysis

Multimodal reasoning model for visual analysis, planning, and tool use

Cohere command model for multilingual enterprise agents, tools, and chat

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Smaller o-series reasoner for economical coding, math, and planning tasks

O-series reasoning model for hard analysis, math, coding, and planning

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Web-grounded Sonar for multi-step research questions that need cited reasoning

Open GPT reasoning model for self-hosted agents and controllable deployments

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Open GPT reasoning model for self-hosted agents and controllable deployments

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Efficient model for low-latency assistance, extraction, and routine automation

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding