[ { "input_cost_per_second": 0.00003333, "output_cost_per_second": 0, "model_id": "assemblyai/best", "model_name": "Best", "provider_id": "assemblyai", "provider_name": "AssemblyAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00010278, "output_cost_per_second": 0, "model_id": "assemblyai/nano", "model_name": "Nano", "provider_id": "assemblyai", "provider_name": "AssemblyAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/", "model_id": "aws_polly/generative", "model_name": "Generative", "provider_id": "aws", "provider_name": "AWS", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.0001, "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/", "model_id": "aws_polly/long-form", "model_name": "Long Form", "provider_id": "aws", "provider_name": "AWS", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000016, "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/", "model_id": "aws_polly/neural", "model_name": "Neural", "provider_id": "aws", "provider_name": "AWS", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000004, "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/", "model_id": "aws_polly/standard", "model_name": "Standard", "provider_id": "aws", "provider_name": "AWS", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.00000125, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-mini-transcribe", "model_name": "GPT-4o Mini Transcribe", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ], "model_id": "azure/gpt-4o-mini-tts", "model_name": "GPT-4o Mini TTS", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-transcribe", "model_name": "GPT-4o Transcribe", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-transcribe-diarize", "model_name": "GPT-4o Transcribe Diarize", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0002833333333333333, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "model_id": "azure/gpt-realtime-whisper", "model_name": "GPT Realtime Whisper", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "audio_transcription_config": "azure_speech", "input_cost_per_second": 0.0002777778, "output_cost_per_second": 0, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/speech/azure-stt", "model_name": "Azure STT", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "source": "https://azure.microsoft.com/en-us/pricing/calculator/", "model_id": "azure/speech/azure-tts", "model_name": "Azure TTS", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "source": "https://azure.microsoft.com/en-us/pricing/calculator/", "model_id": "azure/speech/azure-tts-hd", "model_name": "Azure TTS HD", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "model_id": "azure/tts-1", "model_name": "TTS 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "model_id": "azure/tts-1-hd", "model_name": "TTS 1 HD", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "model_id": "azure/whisper-1", "model_name": "Whisper 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base", "model_name": "Base", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-conversationalai", "model_name": "Base Conversationalai", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-finance", "model_name": "Base Finance", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-general", "model_name": "Base General", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-meeting", "model_name": "Base Meeting", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-phonecall", "model_name": "Base Phonecall", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-video", "model_name": "Base Video", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00020833, "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/base-voicemail", "model_name": "Base Voicemail", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00024167, "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/enhanced", "model_name": "Enhanced", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00024167, "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/enhanced-finance", "model_name": "Enhanced Finance", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00024167, "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/enhanced-general", "model_name": "Enhanced General", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00024167, "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/enhanced-meeting", "model_name": "Enhanced Meeting", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00024167, "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/enhanced-phonecall", "model_name": "Enhanced Phonecall", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova", "model_name": "Nova", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2", "model_name": "Nova 2", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-atc", "model_name": "Nova 2 Atc", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-automotive", "model_name": "Nova 2 Automotive", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-conversationalai", "model_name": "Nova 2 Conversationalai", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-drivethru", "model_name": "Nova 2 Drivethru", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-finance", "model_name": "Nova 2 Finance", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-general", "model_name": "Nova 2 General", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-meeting", "model_name": "Nova 2 Meeting", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-phonecall", "model_name": "Nova 2 Phonecall", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-video", "model_name": "Nova 2 Video", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-2-voicemail", "model_name": "Nova 2 Voicemail", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-3", "model_name": "Nova 3", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-3-general", "model_name": "Nova 3 General", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00008667, "metadata": { "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", "original_pricing_per_minute": 0.0052 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-3-medical", "model_name": "Nova 3 Medical", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-general", "model_name": "Nova General", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00007167, "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/nova-phonecall", "model_name": "Nova Phonecall", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper", "model_name": "Whisper", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper-base", "model_name": "Whisper Base", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper-large", "model_name": "Whisper Large", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper-medium", "model_name": "Whisper Medium", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper-small", "model_name": "Whisper Small", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "deepgram/whisper-tiny", "model_name": "Whisper Tiny", "provider_id": "deepgram", "provider_name": "Deepgram", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00018, "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "elevenlabs/eleven_multilingual_v2", "model_name": "Eleven_multilingual_v2", "provider_id": "elevenlabs", "provider_name": "ElevenLabs", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00018, "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "elevenlabs/eleven_v3", "model_name": "Eleven_v3", "provider_id": "elevenlabs", "provider_name": "ElevenLabs", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0000611, "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", "original_pricing_per_hour": 0.22 }, "output_cost_per_second": 0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "elevenlabs/scribe_v1", "model_name": "Scribe_v1", "provider_id": "elevenlabs", "provider_name": "ElevenLabs", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0000611, "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", "original_pricing_per_hour": 0.22 }, "output_cost_per_second": 0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "elevenlabs/scribe_v1_experimental", "model_name": "Scribe_v1_experimental", "provider_id": "elevenlabs", "provider_name": "ElevenLabs", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "fireworks_ai/accounts/fireworks/models/fireworks-asr-large", "model_name": "Fireworks Asr Large", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2", "model_name": "Fireworks Asr V2", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "tpm": 4000000, "rpm": 10, "model_id": "2.5-flash-preview-tts", "model_name": "2.5 Flash Preview TTS", "provider_id": "google", "provider_name": "Google", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "gemini-2.5-flash-preview-tts", "model_name": "Gemini 2.5 Flash Preview TTS", "provider_id": "google", "provider_name": "Google", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 10000, "max_output_tokens": 10000, "input_cost_per_character": 0.00005, "max_tokens": 10000, "model_id": "playai-tts", "model_name": "Playai TTS", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00003083, "output_cost_per_second": 0, "model_id": "whisper-large-v3", "model_name": "Whisper Large V3", "provider_id": "groq", "provider_name": "Groq", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00001111, "output_cost_per_second": 0, "model_id": "whisper-large-v3-turbo", "model_name": "Whisper Large V3 Turbo", "provider_id": "groq", "provider_name": "Groq", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.0001, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "minimax/speech-02-hd", "model_name": "Speech 02 HD", "provider_id": "minimax", "provider_name": "MiniMax", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00006, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "minimax/speech-02-turbo", "model_name": "Speech 02 Turbo", "provider_id": "minimax", "provider_name": "MiniMax", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.0001, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "minimax/speech-2.6-hd", "model_name": "Speech 2.6 HD", "provider_id": "minimax", "provider_name": "MiniMax", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00006, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "minimax/speech-2.6-turbo", "model_name": "Speech 2.6 Turbo", "provider_id": "minimax", "provider_name": "MiniMax", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.00000125, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "gpt-4o-mini-transcribe", "model_name": "GPT-4o Mini Transcribe", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.00000125, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "gpt-4o-mini-transcribe-2025-03-20", "model_name": "GPT-4o Mini Transcribe (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.00000125, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "gpt-4o-mini-transcribe-2025-12-15", "model_name": "GPT-4o Mini Transcribe (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ], "model_id": "gpt-4o-mini-tts", "model_name": "GPT-4o Mini TTS", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ], "model_id": "gpt-4o-mini-tts-2025-03-20", "model_name": "GPT-4o Mini TTS (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ], "model_id": "gpt-4o-mini-tts-2025-12-15", "model_name": "GPT-4o Mini TTS (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "gpt-4o-transcribe", "model_name": "GPT-4o Transcribe", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "gpt-4o-transcribe-diarize", "model_name": "GPT-4o Transcribe Diarize", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0002833333333333333, "source": "https://platform.openai.com/docs/models/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "model_id": "gpt-realtime-whisper", "model_name": "GPT Realtime Whisper", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "tts-1", "model_name": "TTS 1", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "tts-1-1106", "model_name": "TTS 1 (Jun 2011)", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "tts-1-hd", "model_name": "TTS 1 HD", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "tts-1-hd-1106", "model_name": "TTS 1 HD (Jun 2011)", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "whisper-1", "model_name": "Whisper 1", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 3e-7, "source": "https://docs.dev.runwayml.com/guides/pricing/", "metadata": { "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." }, "model_id": "runwayml/eleven_multilingual_v2", "model_name": "Eleven_multilingual_v2", "provider_id": "runwayml", "provider_name": "Runwayml", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_audio_token": 0, "model_id": "scaleway/openai/whisper-large-v3", "model_name": "Whisper Large V3", "provider_id": "scaleway", "provider_name": "Scaleway", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_output_tokens": 8000, "max_tokens": 8000, "input_cost_per_second": 0, "output_cost_per_second": 0.0000277778, "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true, "model_id": "soniox/stt-async-v4", "model_name": "STT Async V4", "provider_id": "soniox", "provider_name": "Soniox", "max_input_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_output_tokens": 8000, "max_tokens": 8000, "input_cost_per_second": 0, "output_cost_per_second": 0.0000277778, "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true, "model_id": "soniox/stt-async-v5", "model_name": "STT Async V5", "provider_id": "soniox", "provider_name": "Soniox", "max_input_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "source": "https://cloud.google.com/text-to-speech/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "chirp", "model_name": "Chirp", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00026667, "metadata": { "calculation": "$0.016/60 seconds = $0.00026667 per second", "original_pricing_per_minute": 0.016 }, "source": "https://cloud.google.com/speech-to-text/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "chirp_3", "model_name": "Chirp_3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "watsonx/whisper-large-v3-turbo", "model_name": "Whisper Large V3 Turbo", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]