// On-device inference workers exposed as catalog models.

provider "local" {
	default-model "lfm2.5-230m"
	allow-unauthenticated #true

	seed api="local-inference" base-url="local://inference" bundle="always" {
		model "kokoro" name="Kokoro-82M" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "parakeet-tdt-0.6b-v3" name="Parakeet TDT 0.6B v3" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "nemotron-streaming-en-0.6b" name="Nemotron Speech 0.6B (Streaming English)" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "whisper-base" name="Whisper Base" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "whisper-small" name="Whisper Small" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "whisper-large-v3-turbo" name="Whisper Large v3 Turbo" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "lfm2.5-230m" name="LFM2.5 230M" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "lfm2.5-350m" name="LFM2.5 350M" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "falcon-h1-90m" name="Falcon H1 Tiny 90M" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "qwen3-1.7b" name="Qwen3 1.7B" {
			reasoning #true
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "llama3.2:3b" name="Llama 3.2 3B" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "gemma-3-1b" name="Gemma 3 1B" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "qwen2.5-1.5b" name="Qwen2.5 1.5B" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
		model "lfm2-1.2b" name="LFM2 1.2B" {
			reasoning #false
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits
			supports-tools #false
		}
	}

	models "kokoro" {
		kind "tts"
	}
	models "parakeet-tdt-0.6b-v3" "nemotron-streaming-en-0.6b" "whisper-*" {
		kind "stt"
	}
	models "lfm*" "falcon-*" "qwen*" "llama3.2:3b" "gemma-3-1b" {
		kind "tiny"
	}
}