{"service":"GEDX402 Media","role":"shard","hub":"https://gedx402.com","pricing":{"formula":"max(floor, (neurons/1000)*NEURON_USD_RATE*MARKUP_MULTIPLIER+FACILITATOR_BUFFER_USD)","neuron_usd_rate":0.011,"markup_multiplier":2.5,"facilitator_buffer_usd":0.002,"dynamic":true},"payments":{"asset":"USDC","facilitator":"coinbase-cdp","networks":[{"id":"base","label":"Base","caip":"eip155:8453","asset":"USDC","family":"evm"}],"primary_network":"base"},"routes":[{"path":"/v1/asr/flux","method":"GET","model":"@cf/deepgram/flux","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain","voice-agent","flux-asr"],"prominence":"hero","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/asr/flux","summary":"Flux Speech-to-Text","description":"Conversational speech recognition with Flux (@cf/deepgram/flux) for voice agents and CDP Bazaar discovery. WebSocket-only on media.gedx402.com: GET with Upgrade, encoding=linear16, and sample_rate (Hz); stream PCM and receive turn events. Agent recipe: GET /v1/asr/flux → POST /v1/asr/smart-turn-v2 → POST /v1/chat/fast → POST /v1/tts/aura-2-en. Discover bundle: GET /v1/models?bundle=voice. Billed by audio duration.","floor_usd":0.008,"price_usd":0.011625,"price_display":"$0.012","estimated_neurons":350,"worst_case_price_usd":0.09825,"worst_case_price_display":"$0.098","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/asr/smart-turn-v2","method":"POST","model":"@cf/pipecat-ai/smart-turn-v2","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain","voice-agent","smart-turn"],"prominence":"hero","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/asr/smart-turn-v2","summary":"Smart Turn V2 Speech-to-Text","description":"End-of-turn detection with Smart Turn V2 (@cf/pipecat-ai/smart-turn-v2) for voice agents. POST base64 audio chunk; returns whether the speaker finished their turn. Use alongside WebSocket GET /v1/asr/flux for streaming ASR and POST /v1/tts/aura-1 or /v1/tts/aura-2-en for replies. Bundle: GET /v1/models?bundle=voice.","floor_usd":0.002,"price_usd":0.0020275000000000002,"price_display":"$0.0020","estimated_neurons":1,"worst_case_price_usd":0.0020825,"worst_case_price_display":"$0.0021","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/tts/aura-2-en","method":"POST","model":"@cf/deepgram/aura-2-en","kind":"tts","tags":["vision","audio","tts","asr","usdc","multi-chain","voice-agent"],"prominence":"hero","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/tts/aura-2-en","summary":"Aura 2 EN Text-to-Speech","description":"English speech synthesis with Aura 2 EN (@cf/deepgram/aura-2-en). POST text; returns audio bytes billed by character count. Recommended TTS for English voice agents after POST /v1/chat/fast. Bundle: GET /v1/models?bundle=voice.","floor_usd":0.012,"price_usd":0.03951,"price_display":"$0.040","estimated_neurons":1364,"worst_case_price_usd":0.302025,"worst_case_price_display":"$0.302","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/tts/aura-1","method":"POST","model":"@cf/deepgram/aura-1","kind":"tts","tags":["vision","audio","tts","asr","usdc","multi-chain","voice-agent"],"prominence":"hero","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/tts/aura-1","summary":"Aura 1 Text-to-Speech","description":"Synthesize speech from text with Aura 1 (@cf/deepgram/aura-1). POST text; returns audio bytes billed by character count. Voice-agent output leg — pair with GET /v1/asr/flux and POST /v1/asr/smart-turn-v2. Bundle: GET /v1/models?bundle=voice.","floor_usd":0.008,"price_usd":0.020755000000000003,"price_display":"$0.021","estimated_neurons":682,"worst_case_price_usd":0.1520125,"worst_case_price_display":"$0.152","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/guard","method":"POST","model":"@cf/meta/llama-guard-3-8b","kind":"guard","tags":["vision","audio","tts","asr","usdc","multi-chain","guard"],"prominence":"hero","alias_of":"/v1/guard/llama-guard-3-8b","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/guard","summary":"Safety Guard","description":"Safety moderation with Llama Guard 3 8B (@cf/meta/llama-guard-3-8b). Routes to Llama Guard 3; POST messages[] to classify prompt/response policy violations before downstream LLM calls.","floor_usd":0.01,"price_usd":0.01,"price_display":"$0.010","estimated_neurons":23,"worst_case_price_usd":0.01,"worst_case_price_display":"$0.010","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/voice/sessions","method":"POST","model":"gedx402-voice-session","kind":"voice","tags":["vision","audio","tts","asr","usdc","multi-chain","voice","voice-agent"],"prominence":"hero","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/voice/sessions","summary":"Gedx402 Voice Session Inference","description":"Single-hop voice agent session on media.gedx402.com — one x402 payment prepays Flux WebSocket streaming plus smart-turn, chat/fast, and TTS loop credits. POST optional budget {duration_minutes, max_turns}; returns session_id, session_token, routes, and credits. USDC per request (see npm run pricing:report) wire settlement (budget caps apply). Send session_token on bundle routes (header X-Voice-Session-Token, query param on flux WS, or body) — no 402 until credits exhausted. Bundle hero: GET /v1/models?bundle=voice.","floor_usd":0.08,"price_usd":1.494375,"price_display":"$1.494","estimated_neurons":0,"worst_case_price_usd":28.110424999999996,"worst_case_price_display":"$28.110","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/asr/nova-3","method":"POST","model":"@cf/deepgram/nova-3","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/asr/nova-3","summary":"Nova 3 Speech-to-Text","description":"Transcribe speech to text with Nova 3 (@cf/deepgram/nova-3). POST audio (base64) or audio URL; returns transcript text billed by audio duration.","floor_usd":0.008,"price_usd":0.008517499999999999,"price_display":"$0.0085","estimated_neurons":237,"worst_case_price_usd":0.06700999999999999,"worst_case_price_display":"$0.067","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/asr/whisper-large-v3-turbo","method":"POST","model":"@cf/openai/whisper-large-v3-turbo","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/asr/whisper-large-v3-turbo","summary":"Whisper Large V3 Turbo Speech-to-Text","description":"Transcribe speech to text with Whisper Large V3 Turbo (@cf/openai/whisper-large-v3-turbo). POST audio (base64) or audio URL; returns transcript text billed by audio duration.","floor_usd":0.006,"price_usd":0.006,"price_display":"$0.0060","estimated_neurons":24,"worst_case_price_usd":0.008435,"worst_case_price_display":"$0.0084","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/asr/whisper-tiny-en","method":"POST","model":"@cf/openai/whisper-tiny-en","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/asr/whisper-tiny-en","summary":"Whisper Tiny EN Speech-to-Text","description":"Transcribe speech to text with Whisper Tiny EN (@cf/openai/whisper-tiny-en). POST audio (base64) or audio URL; returns transcript text billed by audio duration.","floor_usd":0.003,"price_usd":0.003,"price_display":"$0.0030","estimated_neurons":21,"worst_case_price_usd":0.007665,"worst_case_price_display":"$0.0077","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/speech/transcribe","method":"POST","model":"@cf/openai/whisper","kind":"audio","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/speech/transcribe","summary":"Speech-to-Text","description":"Transcribe speech to text with Whisper (@cf/openai/whisper). POST audio (base64) or audio URL; returns transcript text billed by audio duration.","floor_usd":0.006,"price_usd":0.006,"price_display":"$0.0060","estimated_neurons":21,"worst_case_price_usd":0.007665,"worst_case_price_display":"$0.0077","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/tts/aura-2-es","method":"POST","model":"@cf/deepgram/aura-2-es","kind":"tts","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/tts/aura-2-es","summary":"Aura 2 ES Text-to-Speech","description":"Synthesize speech from text with Aura 2 ES (@cf/deepgram/aura-2-es). POST text; returns audio bytes billed by character count.","floor_usd":0.012,"price_usd":0.03951,"price_display":"$0.040","estimated_neurons":1364,"worst_case_price_usd":0.302025,"worst_case_price_display":"$0.302","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/tts/melotts","method":"POST","model":"@cf/myshell-ai/melotts","kind":"tts","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/tts/melotts","summary":"Melotts Text-to-Speech","description":"Synthesize speech from text with Melotts (@cf/myshell-ai/melotts). POST text; returns audio bytes billed by character count.","floor_usd":0.005,"price_usd":0.005,"price_display":"$0.0050","estimated_neurons":10,"worst_case_price_usd":0.005,"worst_case_price_display":"$0.0050","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/caption/llava-1.5-7b-hf","method":"POST","model":"@cf/llava-hf/llava-1.5-7b-hf","kind":"caption","tags":["vision","audio","tts","asr","usdc","multi-chain","caption"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/caption/llava-1.5-7b-hf","summary":"Llava 1.5 7B Hf Image Captioning","description":"Generate a natural-language caption for an image with Llava 1.5 7B Hf (@cf/llava-hf/llava-1.5-7b-hf). POST image data; returns descriptive text.","floor_usd":0.015,"price_usd":0.22307249999999998,"price_display":"$0.223","estimated_neurons":8039,"worst_case_price_usd":0.5541175,"worst_case_price_display":"$0.554","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/caption/uform-gen2-qwen-500m","method":"POST","model":"@cf/unum/uform-gen2-qwen-500m","kind":"caption","tags":["vision","audio","tts","asr","usdc","multi-chain","caption"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/caption/uform-gen2-qwen-500m","summary":"Uform Gen2 Qwen 500m Image Captioning","description":"Generate a natural-language caption for an image with Uform Gen2 Qwen 500m (@cf/unum/uform-gen2-qwen-500m). POST image data; returns descriptive text.","floor_usd":0.008,"price_usd":0.13993999999999998,"price_display":"$0.140","estimated_neurons":5016,"worst_case_price_usd":0.41537999999999997,"worst_case_price_display":"$0.415","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/detect/detr-resnet-50","method":"POST","model":"@cf/facebook/detr-resnet-50","kind":"detect","tags":["vision","audio","tts","asr","usdc","multi-chain","detect"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/detect/detr-resnet-50","summary":"Detr Resnet 50 Object Detection","description":"Detect objects in an image with Detr Resnet 50 (@cf/facebook/detr-resnet-50). POST base64 image; returns bounding boxes and labels.","floor_usd":0.003,"price_usd":0.0042,"price_display":"$0.0042","estimated_neurons":80,"worst_case_price_usd":0.0042,"worst_case_price_display":"$0.0042","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/guard/llama-guard-3-8b","method":"POST","model":"@cf/meta/llama-guard-3-8b","kind":"guard","tags":["vision","audio","tts","asr","usdc","multi-chain","guard"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/guard/llama-guard-3-8b","summary":"Llama Guard 3 8B Safety Guard","description":"Run safety moderation with Llama Guard 3 8B (@cf/meta/llama-guard-3-8b). POST messages or content to classify policy violations before downstream LLM calls.","floor_usd":0.01,"price_usd":0.01,"price_display":"$0.010","estimated_neurons":23,"worst_case_price_usd":0.01,"worst_case_price_display":"$0.010","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/vision/describe","method":"POST","model":"@cf/meta/llama-3.2-11b-vision-instruct","kind":"vision","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/vision/describe","summary":"Image Description","description":"Describe or answer questions about an image with Llama 3.2 11B Vision Instruct (@cf/meta/llama-3.2-11b-vision-instruct). POST image (base64) plus optional prompt; multimodal pricing includes image and text neurons.","floor_usd":0.025,"price_usd":0.33288,"price_display":"$0.333","estimated_neurons":12032,"worst_case_price_usd":0.8837324999999999,"worst_case_price_display":"$0.884","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."},{"path":"/v1/vision/llama-3.2-11b","method":"POST","model":"@cf/meta/llama-3.2-11b-vision-instruct","kind":"vision","tags":["vision","audio","tts","asr","usdc","multi-chain"],"prominence":"standard","shard":"media","origin":"https://media.gedx402.com","url":"https://media.gedx402.com/v1/vision/llama-3.2-11b","summary":"Llama 3.2 11B Vision Instruct Vision","description":"Describe or answer questions about an image with Llama 3.2 11B Vision Instruct (@cf/meta/llama-3.2-11b-vision-instruct). POST image (base64) plus optional prompt; multimodal pricing includes image and text neurons.","floor_usd":0.025,"price_usd":0.33288,"price_display":"$0.333","estimated_neurons":12032,"worst_case_price_usd":0.8837324999999999,"worst_case_price_display":"$0.884","middleware_price_note":"402 uses worst-case catalog estimates with account COGS from account-cogs.json; npm run pricing:sync refreshes neuron rates."}],"route_count":18,"catalog_version":6}