ReplicateService details
Offering
Replicate Open-Source AI Model API
Offering detailsUsage-based$0.0002 per second CPU (varies by model)2 regions
10,000+ Models: 10,000+; Custom Model Deployment: true; +3 more
Compare · AI Inference
What's on offer.
APIs for running AI and machine learning model inference.
Offerings
50 offerings on this page with service context, pricing, regions, and links.
Resemble AIService details
Offering
Resemble AI Voice API
Offering detailsUsage-based$0.006 per second of audio1 region
Instant Voice Cloning: 3 seconds of audio; Real-Time Synthesis: < 200ms latency; +3 more
RunPodService details
Offering
RunPod Serverless AI Inference
Offering detailsUsage-based$0.0002 per second (RTX 3090)4 regions
Scale to Zero: $0 when idle; Custom Containers: Any Docker image; +3 more
Runway ResearchService details
Offering
Runway Research API
Offering detailsUsage-based$0.050 per generation credit1 region
Gen-3 Alpha: Text-to-video API; Image-to-Video: Animate reference images; +3 more
SalesforceService details
Offering
Salesforce Einstein AI
Offering detailsSubscription$50 per user/month (Einstein for Sales)4 regions
Einstein Copilot: true; Predictive Scoring: true; +2 more
SambaNova SystemsService details
Offering
SambaNova Cloud AI Inference
Offering detailsUsage-based$0.0005 per 1K tokens1 region
World-Record Speed: 2,300+ tokens/second; OpenAI Compatible: Drop-in replacement; +3 more
SAP Business Technology PlatformService details
Offering
SAP AI Core
Offering detailsUsage-based$0.020 per capability unit hour3 regions
Generative AI Hub: Multi-LLM gateway; Custom Model Training: Kubernetes-based; +2 more
Scale AIService details
Offering
Scale Generative AI Platform
Offering detailsUsage-basedFree1 region
RLHF at Scale: Human feedback pipelines; Model Evaluation: Benchmarks & red teaming; +2 more
Snorkel AIService details
Offering
Snorkel Flow Model Training
Offering detailsSubscriptionFree1 region
Programmatic Labeling: Labeling functions; LLM-Assisted Labeling: Foundation model bootstrap; +2 more
SnowflakeService details
Offering
Snowflake Cortex AI
Offering detailsUsage-based$0.040 per 1M tokens (Llama 3 8B)4 regions
No Data Movement: AI runs in Snowflake; LLM Functions: Complete, Summarize, Translate; +2 more
SoraService details
Offering
Sora Video Generation API
Offering detailsSubscription$20 per month (ChatGPT Plus)1 region
Text-to-Video: Up to 1080p, 20 seconds; Image-to-Video: Animate still images; +3 more
Stability AIService details
Offering
Stability AI Inference API
Offering detailsUsage-based$0.065 per image (SD3.5)1 region
Stable Diffusion 3.5: State-of-the-art image generation; Image Editing: Inpaint, outpaint, transform; +3 more
Stability AI APIService details
Offering
Stability AI API - Stable Diffusion
Offering detailsUsage-based$0.003 per image (SDXL 512px)1 region
Text-to-Image: SDXL & SD3 models; Image-to-Image: Guided transformation; +3 more
StepFunService details
Offering
Step 3.5 Flash
Offering detailsPay-as-you-go$0.100 1M input tokens0 regions
Context Window: 262144 tokens; Input Modalities: text
StepFunService details
Offering
Step 3.5 Flash
Offering detailsFreePrice pending0 regions
Context Window: 256000 tokens; Input Modalities: text
TabnineService details
Offering
Tabnine AI Code Inference
Offering detailsFreemiumFree1 region
Private Deployment: Self-hosted or VPC; Custom Model Training: Codebase-specific models; +3 more
TencentService details
Offering
Hunyuan A13B Instruct
Offering detailsPay-as-you-go$0.140 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
Tencent Cloud AIService details
Offering
Tencent Cloud AI — NLP, Vision & LLM APIs
Offering detailsUsage-based$0.0008 per 1000 tokens (Hunyuan Lite)5 regions
Hunyuan LLM: Bilingual Chinese-English LLM; Computer Vision: Face, OCR, image recognition; +3 more
TenstorrentService details
Offering
Tenstorrent AI Inference Cloud
Offering detailsUsage-based$0.500 per hour (Wormhole card)1 region
LLM Inference: Cost-efficient token generation; Open Software Stack: TT-Buda inference framework; +1 more
Together AIService details
Offering
Together AI — Open-Source Model Inference Platform
Offering detailsUsage-based$0.0001 per 1M tokens (Llama 3.2 8B)3 regions
Model Catalog: 100+ open-source models; Serverless Inference: Pay-per-token pricing; +3 more
Together AIService details
Offering
DeepSeek V3.1 on Together AI
Offering detailsPay-as-you-go$0.600 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Together AIService details
Offering
GLM-5 on Together AI
Offering detailsPay-as-you-go$1 1M input tokens0 regions
Context Window: 202752 tokens; Input Modalities: text
Together AIService details
Offering
GPT-OSS 120B on Together AI
Offering detailsPay-as-you-go$0.150 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Together AIService details
Offering
GPT-OSS 20B on Together AI
Offering detailsPay-as-you-go$0.050 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Together AIService details
Offering
Kimi K2.5 on Together AI
Offering detailsPay-as-you-go$0.500 1M input tokens0 regions
Context Window: 256000 tokens; Input Modalities: text, image
Together AIService details
Offering
Llama 4 Maverick on Together AI
Offering detailsPay-as-you-go$0.270 1M input tokens0 regions
Context Window: 524288 tokens; Input Modalities: text, image
Together AIService details
Offering
Qwen3.5 397B on Together AI
Offering detailsPay-as-you-go$0.600 1M input tokens0 regions
Context Window: 262144 tokens; Input Modalities: text
Together AIService details
Offering
Qwen3 Coder 480B on Together AI
Offering detailsPay-as-you-go$2 1M input tokens0 regions
Context Window: 256000 tokens; Input Modalities: text
TSMCService details
Offering
TSMC AI Chip Fabrication
Offering detailsCustom$20,000 per wafer (N5 process)4 regions
Leading-Edge Processes: N3 and N2 nodes; CoWoS Packaging: HBM memory integration; +1 more
UnslothService details
Offering
Unsloth Enterprise
Offering detailsSubscriptionFree1 region
2-5x Faster Fine-tuning: Custom CUDA kernels; 80% Memory Reduction: Fit larger models on smaller GPUs; +2 more
UnslothService details
Offering
Unsloth AI Inference Optimization
Offering detailsFreemiumFree1 region
Triton Kernels: Custom CUDA rewrite; Memory Reduction: Up to 70% less VRAM; +3 more
UpstageService details
Offering
Upstage Solar API — Enterprise LLM & Document AI
Offering detailsUsage-based$0.0001 per 1K tokens (Solar Mini)1 region
Solar LLM: 10.7B parameter, top leaderboard; Document Parse API: Structured data extraction; +3 more
VercelService details
Offering
Vercel AI SDK & Inference
Offering detailsFreemiumFree1 region
Unified Streaming API: 20+ AI providers; AI Gateway: Multi-provider routing; +3 more
vLLMService details
Offering
vLLM — High-Throughput LLM Inference Engine
Offering detailsOpen sourceFree1 region
PagedAttention: Near 100% KV cache utilization; Throughput: 2-24x vs HuggingFace Transformers; +3 more
WhyLabsService details
Offering
WhyLabs LLM Monitoring
Offering detailsFreemiumFree1 region
Prompt Injection: Real-time detection; Toxicity Detection: Content safety scoring; +3 more
WriterService details
Offering
Writer — Full-Stack Enterprise Generative AI
Offering detailsSubscription$18 per user per month1 region
Palmyra LLM: Enterprise-tuned LLM family; Knowledge Graph: Structured enterprise knowledge; +3 more
WriterService details
Offering
Palmyra X5
Offering detailsPay-as-you-go$0.600 1M input tokens0 regions
Context Window: 1040000 tokens; Input Modalities: text
WritesonicService details
Offering
Writesonic — AI Writing & SEO Platform
Offering detailsFreemiumFree1 region
Chatsonic: ChatGPT alternative with web search; Content Templates: 100+ templates; +3 more
xAIService details
Offering
xAI API (Grok Models)
Offering detailsUsage-based$0.0002 per 1K input tokens (Grok-2-Mini)1 region
Real-Time Data: X (Twitter) integration; Context Window: 128K-131K tokens; +3 more
xAIService details
Offering
Grok (xAI)
Offering detailsUsage-based$0.000 per input token (grok-4-1-fast)1 region
Real-time X Data: true; Context Window: 131K tokens; +3 more
xAIService details
Offering
Grok 3
Offering detailsPay-as-you-go$3 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
xAIService details
Offering
Grok 3 Beta
Offering detailsPay-as-you-go$3 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
xAIService details
Offering
Grok 3 Mini
Offering detailsPay-as-you-go$0.300 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
xAIService details
Offering
Grok 3 Mini Beta
Offering detailsPay-as-you-go$0.300 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
xAIService details
Offering
Grok 4
Offering detailsPay-as-you-go$3 1M input tokens0 regions
Context Window: 256000 tokens; Input Modalities: image, text, file
xAIService details
Offering
Grok 4.1 Fast
Offering detailsPay-as-you-go$0.200 1M input tokens0 regions
Context Window: 2000000 tokens; Input Modalities: text, image, file
xAIService details
Offering
Grok 4.20
Offering detailsPay-as-you-go$2 1M input tokens0 regions
Context Window: 2000000 tokens; Input Modalities: text, image
xAIService details
Offering
Grok 4.20 Beta
Offering detailsPay-as-you-go$3 1M input tokens0 regions
Context Window: 2000000 tokens; Input Modalities: text, image
xAIService details
Offering
Grok 4.20 Multi-Agent
Offering detailsPay-as-you-go$2 1M input tokens0 regions
Context Window: 2000000 tokens; Input Modalities: text, image, file
xAIService details
Offering
Grok 4 Fast
Offering detailsPay-as-you-go$0.200 1M input tokens0 regions
Context Window: 2000000 tokens; Input Modalities: text, image
| Service | Offering | Pricing model | Starting price | Regions | Features | Links |
|---|---|---|---|---|---|---|
ReplicateService details | Replicate Open-Source AI Model API Offering details | Usage-based | $0.0002 per second CPU (varies by model) | 2 | 10,000+ Models: 10,000+; Custom Model Deployment: true; +3 more | |
Resemble AIService details | Resemble AI Voice API Offering details | Usage-based | $0.006 per second of audio | 1 | Instant Voice Cloning: 3 seconds of audio; Real-Time Synthesis: < 200ms latency; +3 more | |
RunPodService details | RunPod Serverless AI Inference Offering details | Usage-based | $0.0002 per second (RTX 3090) | 4 | Scale to Zero: $0 when idle; Custom Containers: Any Docker image; +3 more | |
Runway ResearchService details | Runway Research API Offering details | Usage-based | $0.050 per generation credit | 1 | Gen-3 Alpha: Text-to-video API; Image-to-Video: Animate reference images; +3 more | |
SalesforceService details | Salesforce Einstein AI Offering details | Subscription | $50 per user/month (Einstein for Sales) | 4 | Einstein Copilot: true; Predictive Scoring: true; +2 more | |
SambaNova SystemsService details | SambaNova Cloud AI Inference Offering details | Usage-based | $0.0005 per 1K tokens | 1 | World-Record Speed: 2,300+ tokens/second; OpenAI Compatible: Drop-in replacement; +3 more | |
SAP Business Technology PlatformService details | SAP AI Core Offering details | Usage-based | $0.020 per capability unit hour | 3 | Generative AI Hub: Multi-LLM gateway; Custom Model Training: Kubernetes-based; +2 more | |
Scale AIService details | Scale Generative AI Platform Offering details | Usage-based | Free | 1 | RLHF at Scale: Human feedback pipelines; Model Evaluation: Benchmarks & red teaming; +2 more | |
Snorkel AIService details | Snorkel Flow Model Training Offering details | Subscription | Free | 1 | Programmatic Labeling: Labeling functions; LLM-Assisted Labeling: Foundation model bootstrap; +2 more | |
SnowflakeService details | Snowflake Cortex AI Offering details | Usage-based | $0.040 per 1M tokens (Llama 3 8B) | 4 | No Data Movement: AI runs in Snowflake; LLM Functions: Complete, Summarize, Translate; +2 more | |
SoraService details | Sora Video Generation API Offering details | Subscription | $20 per month (ChatGPT Plus) | 1 | Text-to-Video: Up to 1080p, 20 seconds; Image-to-Video: Animate still images; +3 more | |
Stability AIService details | Stability AI Inference API Offering details | Usage-based | $0.065 per image (SD3.5) | 1 | Stable Diffusion 3.5: State-of-the-art image generation; Image Editing: Inpaint, outpaint, transform; +3 more | |
Stability AI APIService details | Stability AI API - Stable Diffusion Offering details | Usage-based | $0.003 per image (SDXL 512px) | 1 | Text-to-Image: SDXL & SD3 models; Image-to-Image: Guided transformation; +3 more | |
StepFunService details | Step 3.5 Flash Offering details | Pay-as-you-go | $0.100 1M input tokens | 0 | Context Window: 262144 tokens; Input Modalities: text | |
StepFunService details | Step 3.5 Flash Offering details | Free | — | 0 | Context Window: 256000 tokens; Input Modalities: text | |
TabnineService details | Tabnine AI Code Inference Offering details | Freemium | Free | 1 | Private Deployment: Self-hosted or VPC; Custom Model Training: Codebase-specific models; +3 more | |
TencentService details | Hunyuan A13B Instruct Offering details | Pay-as-you-go | $0.140 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
Tencent Cloud AIService details | Tencent Cloud AI — NLP, Vision & LLM APIs Offering details | Usage-based | $0.0008 per 1000 tokens (Hunyuan Lite) | 5 | Hunyuan LLM: Bilingual Chinese-English LLM; Computer Vision: Face, OCR, image recognition; +3 more | |
TenstorrentService details | Tenstorrent AI Inference Cloud Offering details | Usage-based | $0.500 per hour (Wormhole card) | 1 | LLM Inference: Cost-efficient token generation; Open Software Stack: TT-Buda inference framework; +1 more | |
Together AIService details | Together AI — Open-Source Model Inference Platform Offering details | Usage-based | $0.0001 per 1M tokens (Llama 3.2 8B) | 3 | Model Catalog: 100+ open-source models; Serverless Inference: Pay-per-token pricing; +3 more | |
Together AIService details | DeepSeek V3.1 on Together AI Offering details | Pay-as-you-go | $0.600 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Together AIService details | GLM-5 on Together AI Offering details | Pay-as-you-go | $1 1M input tokens | 0 | Context Window: 202752 tokens; Input Modalities: text | |
Together AIService details | GPT-OSS 120B on Together AI Offering details | Pay-as-you-go | $0.150 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Together AIService details | GPT-OSS 20B on Together AI Offering details | Pay-as-you-go | $0.050 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Together AIService details | Kimi K2.5 on Together AI Offering details | Pay-as-you-go | $0.500 1M input tokens | 0 | Context Window: 256000 tokens; Input Modalities: text, image | |
Together AIService details | Llama 4 Maverick on Together AI Offering details | Pay-as-you-go | $0.270 1M input tokens | 0 | Context Window: 524288 tokens; Input Modalities: text, image | |
Together AIService details | Qwen3.5 397B on Together AI Offering details | Pay-as-you-go | $0.600 1M input tokens | 0 | Context Window: 262144 tokens; Input Modalities: text | |
Together AIService details | Qwen3 Coder 480B on Together AI Offering details | Pay-as-you-go | $2 1M input tokens | 0 | Context Window: 256000 tokens; Input Modalities: text | |
TSMCService details | TSMC AI Chip Fabrication Offering details | Custom | $20,000 per wafer (N5 process) | 4 | Leading-Edge Processes: N3 and N2 nodes; CoWoS Packaging: HBM memory integration; +1 more | |
UnslothService details | Unsloth Enterprise Offering details | Subscription | Free | 1 | 2-5x Faster Fine-tuning: Custom CUDA kernels; 80% Memory Reduction: Fit larger models on smaller GPUs; +2 more | |
UnslothService details | Unsloth AI Inference Optimization Offering details | Freemium | Free | 1 | Triton Kernels: Custom CUDA rewrite; Memory Reduction: Up to 70% less VRAM; +3 more | |
UpstageService details | Upstage Solar API — Enterprise LLM & Document AI Offering details | Usage-based | $0.0001 per 1K tokens (Solar Mini) | 1 | Solar LLM: 10.7B parameter, top leaderboard; Document Parse API: Structured data extraction; +3 more | |
VercelService details | Vercel AI SDK & Inference Offering details | Freemium | Free | 1 | Unified Streaming API: 20+ AI providers; AI Gateway: Multi-provider routing; +3 more | |
vLLMService details | vLLM — High-Throughput LLM Inference Engine Offering details | Open source | Free | 1 | PagedAttention: Near 100% KV cache utilization; Throughput: 2-24x vs HuggingFace Transformers; +3 more | |
WhyLabsService details | WhyLabs LLM Monitoring Offering details | Freemium | Free | 1 | Prompt Injection: Real-time detection; Toxicity Detection: Content safety scoring; +3 more | |
WriterService details | Writer — Full-Stack Enterprise Generative AI Offering details | Subscription | $18 per user per month | 1 | Palmyra LLM: Enterprise-tuned LLM family; Knowledge Graph: Structured enterprise knowledge; +3 more | |
WriterService details | Palmyra X5 Offering details | Pay-as-you-go | $0.600 1M input tokens | 0 | Context Window: 1040000 tokens; Input Modalities: text | |
WritesonicService details | Writesonic — AI Writing & SEO Platform Offering details | Freemium | Free | 1 | Chatsonic: ChatGPT alternative with web search; Content Templates: 100+ templates; +3 more | |
xAIService details | xAI API (Grok Models) Offering details | Usage-based | $0.0002 per 1K input tokens (Grok-2-Mini) | 1 | Real-Time Data: X (Twitter) integration; Context Window: 128K-131K tokens; +3 more | |
xAIService details | Grok (xAI) Offering details | Usage-based | $0.000 per input token (grok-4-1-fast) | 1 | Real-time X Data: true; Context Window: 131K tokens; +3 more | |
xAIService details | Grok 3 Offering details | Pay-as-you-go | $3 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
xAIService details | Grok 3 Beta Offering details | Pay-as-you-go | $3 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
xAIService details | Grok 3 Mini Offering details | Pay-as-you-go | $0.300 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
xAIService details | Grok 3 Mini Beta Offering details | Pay-as-you-go | $0.300 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
xAIService details | Grok 4 Offering details | Pay-as-you-go | $3 1M input tokens | 0 | Context Window: 256000 tokens; Input Modalities: image, text, file | |
xAIService details | Grok 4.1 Fast Offering details | Pay-as-you-go | $0.200 1M input tokens | 0 | Context Window: 2000000 tokens; Input Modalities: text, image, file | |
xAIService details | Grok 4.20 Offering details | Pay-as-you-go | $2 1M input tokens | 0 | Context Window: 2000000 tokens; Input Modalities: text, image | |
xAIService details | Grok 4.20 Beta Offering details | Pay-as-you-go | $3 1M input tokens | 0 | Context Window: 2000000 tokens; Input Modalities: text, image | |
xAIService details | Grok 4.20 Multi-Agent Offering details | Pay-as-you-go | $2 1M input tokens | 0 | Context Window: 2000000 tokens; Input Modalities: text, image, file | |
xAIService details | Grok 4 Fast Offering details | Pay-as-you-go | $0.200 1M input tokens | 0 | Context Window: 2000000 tokens; Input Modalities: text, image |
Showing 451–500 of 515 offerings