Models

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

Strongest Claude Opus model for coding, agents, and professional work

Claude model for creative writing, analysis, and controlled agent workflows

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

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

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Everyday Claude agent model for coding, planning, browsing, and general work

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

Open MoE flagship with million-token context for coding and long agent runs

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

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Reasoning-first Gemini preview for agentic coding and complex problem solving

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

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

Default frontier GPT for coding, computer use, research, and knowledge work

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

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

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

Agent-ready GPT for coding and computer-use workflows at a lower cost

DeepSeek chat model for instruction following, coding, and analysis

Reliable GPT generation for broad coding, writing, and tool-assisted product work

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

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

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

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

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

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

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

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

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