Pricing – Replicate (https://replicate.com/pricing) citeturn141view2 [wordlim: 200] Crawled: today; Content type: text/html; Source: open({"ref_id":"https://replicate.com/pricing","lineno":null}); Total lines: 344 L0: 【0†Explore】【1†Pricing】【2†Enterprise】【3†Docs】【4†Blog】【5†Sign in】【5†Try for free】 L1: L2: * * * L3: L4: 【6†Compare models in the Playground】 L5: L6: # Pricing L7: L8: You only pay for what you use on Replicate. Some models are billed by hardware and time, others by input and output. L9: #### 【7†Public models】 L10: L11: Thousands of open-source machine learning models have been contributed by our community and more are added every day. We also host a wide variety of proprietary models. L12: L13: Most models are billed by the time they take to run. The 【8†price-per-second】 varies according to the hardware in use. When running or training one of these public models, you only pay for the time it takes to process your request. L14: L15: Some models are billed by input and output. We've included some examples below. L16: You'll find estimates for how much any model will cost you on the model's page. L17: 【9†black-forest-labs/flux-1.1-pro Faster, better FLUX Pro. L18: Text-to-image model with excellent image quality, prompt adherence, and output diversity.$0.04 / output image】【10†black-forest-labs/flux-dev A 12 billion parameter rectified flow transformer capable of generating images from text descriptions$0.025 / output image】【11†black-forest-labs/flux-schnell The fastest image generation model tailored for local development and personal use$3.00 / thousand output images】【12†deepseek-ai/deepseek-r1 A reasoning model trained with reinforcement learning, on par with OpenAI o1$0.01 / thousand output tokens$3.75 / million input tokens】【13†ideogram-ai/ideogram-v3-quality The highest quality Ideogram v3 model. L19: v3 creates images with stunning realism, creative designs, and consistent styles$0.09 / output image】【14†recraft-ai/recraft-v3 Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. L20: As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis$0.04 / output image】【15†wavespeedai/wan-2.1-i2v-480p Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.$0.09 / second of output video】【16†wavespeedai/wan-2.1-i2v-720p Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.$0.25 / second of output video】 L21: #### 【17†Private models】 L22: L23: You aren't limited to the public models on Replicate: you can deploy your own custom models using 【18†Cog†github.com】, our open-source tool for packaging machine learning models. L24: Unlike public models, most private models (with the exception of 【19†fast booting fine-tunes】) run on dedicated hardware so you don't have to share a queue with anyone else. This means you pay for all the time instances of the model are online: the time they spend setting up; the time they spend idle, waiting for requests; and the time they spend active, processing your requests. If you get a ton of traffic, we automatically scale up and down to handle the demand. L25: For fast booting fine-tunes you'll only be billed for the time the model is active and processing your requests, so you won't pay for idle time like with other private models. Fast booting fine-tunes are labeled as such in the model's version list. L26: #### 【8†Hardware pricing】 L27: L28: CPU (Small) L29: cpu-small L30: L31: $0.000025/sec L32: $0.09/hr L33: L34: GPU L35: - L36: L37: CPU L38: 1x L39: L40: GPU RAM L41: - L42: L43: RAM L44: 2GB L45: L46: CPU L47: cpu L48: L49: $0.000100/sec L50: $0.36/hr L51: L52: GPU L53: - L54: L55: CPU L56: 4x L57: L58: GPU RAM L59: - L60: L61: RAM L62: 8GB L63: L64: Nvidia A100 (80GB) GPU L65: gpu-a100-large L66: L67: $0.001400/sec L68: $5.04/hr L69: L70: GPU L71: 1x L72: L73: CPU L74: 10x L75: L76: GPU RAM L77: 80GB L78: L79: RAM L80: 144GB L81: L82: 2x Nvidia A100 (80GB) GPU L83: gpu-a100-large-2x L84: L85: $0.002800/sec L86: $10.08/hr L87: L88: GPU L89: 2x L90: L91: CPU L92: 20x L93: L94: GPU RAM L95: 160GB L96: L97: RAM L98: 288GB L99: L100: Nvidia H100 GPU L101: gpu-h100 L102: L103: $0.001525/sec L104: $5.49/hr L105: GPU L106: 1x L107: L108: CPU L109: 13x L110: L111: GPU RAM L112: 80GB L113: L114: RAM L115: 144GB L116: L117: Nvidia L40S GPU L118: gpu-l40s L119: L120: $0.000975/sec L121: $3.51/hr L122: L123: GPU L124: 1x L125: L126: CPU L127: 10x L128: L129: GPU RAM L130: 48GB L131: L132: RAM L133: 65GB L134: L135: 2x Nvidia L40S GPU L136: gpu-l40s-2x L137: L138: $0.001950/sec L139: $7.02/hr L140: L141: GPU L142: 2x L143: L144: CPU L145: 20x L146: L147: GPU RAM L148: 96GB L149: L150: RAM L151: 144GB L152: L153: Nvidia T4 GPU L154: gpu-t4 L155: L156: $0.000225/sec L157: $0.81/hr L158: L159: GPU L160: 1x L161: L162: CPU L163: 4x L164: L165: GPU RAM L166: 16GB L167: L168: RAM L169: 16GB L170: L171: Additional hardware L172: L173: 4x Nvidia A100 (80GB) GPU L174: gpu-a100-large-4x L175: L176: $0.005600/sec L177: $20.16/hr L178: Additional Multi-GPU A100 capacity is available with committed spend contracts. L179: L180: 8x Nvidia A100 (80GB) GPU L181: gpu-a100-large-8x L182: L183: $0.011200/sec L184: $40.32/hr L185: L186: Additional Multi-GPU A100 capacity is available with committed spend contracts. L187: L188: 2x Nvidia H100 GPU L189: gpu-h100-2x L190: L191: $0.003050/sec L192: $10.98/hr L193: L194: Additional Multi-GPU H100 capacity is available with committed spend contracts. L195: L196: 4x Nvidia H100 GPU L197: gpu-h100-4x L198: L199: $0.006100/sec L200: $21.96/hr L201: L202: Additional Multi-GPU H100 capacity is available with committed spend contracts.