Available Models

Models offered natively in the Factory platform.

Anthropic

Model	Multiplier	Best for
Claude Opus 4.7	2x	Anthropic flagship, Max reasoning
Claude Opus 4.6	2×	Previous flagship, Max reasoning
Claude Opus 4.6 Fast	12×	Opus 4.6 tuned for faster responses
Claude Sonnet 4.6	1.2×	Max reasoning at the Sonnet price point
Claude Opus 4.5	2×	Complex reasoning, architecture
Claude Sonnet 4.5	1.2×	Balanced quality/cost
Claude Haiku 4.5	0.4×	Quick edits, routine work

OpenAI

Model	Multiplier	Best for
GPT-5.5	2×	OpenAI flagship, supports Extra High reasoning
GPT-5.5 Fast	5×	GPT-5.5 on a priority service tier
GPT-5.5 Pro	12×	Higher-capability GPT-5.5 variant for research-heavy tasks
GPT-5.4	1×	Large-context GPT model with Extra High reasoning
GPT-5.4 Fast	2×	Faster GPT-5.4 responses
GPT-5.4 Mini	0.3×	Cost-sensitive GPT work
GPT-5.3-Codex	0.7×	Advanced coding with Extra High reasoning
GPT-5.3-Codex Fast	1.4×	Faster GPT-5.3-Codex responses
GPT-5.2	0.7×	General GPT work with Extra High reasoning
GPT-5.2-Codex	0.7×	Advanced coding with Extra High reasoning

Google

Model	Multiplier	Best for
Gemini 3.1 Pro	0.8×	Research, analysis with newer Gemini generation
Gemini 3 Pro	0.8×	Research, analysis
Gemini 3 Flash	0.2×	Fast, cheap for high-volume tasks

Droid Core (Open Models)

Model	Multiplier	Best for
GLM-5.1	0.55×	Newer open-source GLM model when you want stronger quality in Droid Core
Kimi K2.6	0.4×	Cost-sensitive work, supports images, optional High reasoning
Kimi K2.5	0.25×	Cost-sensitive work, supports images
MiniMax M2.7	0.12×	Cheapest option with reasoning support

Custom models

Configure custom models through Bring Your Own Key (BYOK). Custom models use the custom:<alias> model ID format. Context windows, reasoning support, and multipliers depend on the configured provider and model.