Free models

Free models, with automatic quality gates.

Flow AI continuously discovers free-tier hosted models, runs each through a live canary — real tool-calling, structured output, response quality — and promotes only the ones that pass into the default routing pool. When a free model can genuinely do your task, auto routes to it and the tokens cost $0. When it can't, routing escalates to a paid model that finishes the job. No flag to set, nothing to configure.

Currently promoted (25)

Live list — models enter and leave as they pass or fail the canary. Refreshes every few minutes.

ModelContextVerified capabilitiesToken cost
cohere/north-mini-code256Kagentic, function_calling$0
dots-studio/dots-3-note-preview512Kagentic, function_calling, json$0
google/gemma-4-26b-a4b-it262Kagentic, function_calling, json$0
google/gemma-4-31b-it262Kagentic, function_calling, json$0
inclusionai/ling-3.0-flash-fin262Kagentic, function_calling$0
inclusionai/ling-3.0-flash-sante262Kagentic, function_calling$0
inclusionai/ling-3.0-flash262Kagentic, function_calling$0
inclusionai/ling-3.0-tiny262Kagentic, function_calling$0
liquid/lfm-2.5-2.6b66Kagentic, function_calling, json$0
minimax/minimax-m2.7197Kagentic, function_calling, json$0
minimax/minimax-m31Magentic, function_calling, json$0
nvidia/nemotron-3-nano-30b-a3b256Kagentic, function_calling$0
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning256Kagentic, function_calling$0
nvidia/nemotron-3-super-120b-a12b262Kagentic, function_calling, json$0
nvidia/nemotron-3-ultra-550b-a55b1Magentic, function_calling$0
nvidia/nemotron-3.5-lightning1Magentic, function_calling$0
nvidia/nemotron-nano-12b-v2-vl128Kagentic, function_calling$0
nvidia/nemotron-nano-9b-v2128Kagentic, function_calling, json$0
openai/gpt-oss-20b131Kagentic, function_calling, json$0
poolside/laguna-m.1262Kagentic, function_calling$0
poolside/laguna-s-2.1262Kagentic, function_calling$0
poolside/laguna-xs-2.1262Kagentic, function_calling$0
thinkingmachines/inkling-small1Magentic, function_calling$0
thinkingmachines/inkling1Magentic, function_calling$0
z-ai/glm-5.2256Kagentic, function_calling, json$0

Why this is safe to use in production

"Free model" usually means "you get what you pay for": silent tool-calling failures, malformed JSON, empty responses. Flow AI treats free capacity as supply to be verified, not trusted. Every candidate must pass a canary that exercises actual function-calling and output contracts before it can serve traffic, and the router's completion-aware cascade judges every response — a free model that fails your task escalates to a stronger model automatically, and rejected attempts aren't charged.

Try it in the playground, or read the docs — free models are already part of auto.