Google GeminiService details
Offering
Gemma 3 4B
Offering detailsPay-as-you-go$0.040 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text, image
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.
Google GeminiService details
Offering
Gemma 3 4B
Offering detailsFreePrice pending0 regions
Context Window: 32768 tokens; Input Modalities: text, image
Google GeminiService details
Offering
Gemma 3n 2B
Offering detailsFreePrice pending0 regions
Context Window: 8192 tokens; Input Modalities: text
Google GeminiService details
Offering
Gemma 3n 4B
Offering detailsPay-as-you-go$0.020 1M input tokens0 regions
Context Window: 32768 tokens; Input Modalities: text
Google GeminiService details
Offering
Gemma 3n 4B
Offering detailsFreePrice pending0 regions
Context Window: 8192 tokens; Input Modalities: text
Google GeminiService details
Offering
Gemma 4 26B A4B
Offering detailsPay-as-you-go$0.130 1M input tokens0 regions
Context Window: 262144 tokens; Input Modalities: image, text, video
Google GeminiService details
Offering
Gemma 4 31B
Offering detailsPay-as-you-go$0.140 1M input tokens0 regions
Context Window: 262144 tokens; Input Modalities: image, text, video
Google GeminiService details
Offering
Lyria 3 Clip Preview
Offering detailsFreePrice pending0 regions
Context Window: 1048576 tokens; Input Modalities: text, image
Google GeminiService details
Offering
Lyria 3 Pro Preview
Offering detailsFreePrice pending0 regions
Context Window: 1048576 tokens; Input Modalities: text, image
Google WorkspaceService details
Offering
Gemini for Google Workspace
Offering detailsSubscription$20 per user/month (Gemini Business add-on)1 region
Gmail AI: Draft, summarize, reply; Docs AI: Write, rewrite, proofread; +2 more
GrammarlyService details
Offering
Grammarly AI Writing Assistant
Offering detailsFreemiumFree1 region
Real-time Suggestions: true; Generative AI Writing: true; +3 more
GrammarlyService details
Offering
Grammarly Business
Offering detailsSubscription$15 per member/month (billed annually, minimum 3 seats)1 region
Style Guide: Company style guide enforcement; Brand Tone: Custom tone settings; +2 more
GrammarlyService details
Offering
Grammarly GO (AI Writing Features)
Offering detailsSubscription$12 per month (Pro plan, billed annually)1 region
Generation: Draft emails and documents; Rewriting: Full-paragraph rewrites; +2 more
GraphcoreService details
Offering
Graphcore Poplar SDK
Offering detailsFreeFree1 region
Compiler: Poplar Graph Compiler; PyTorch Integration: PopTorch; +2 more
GroqService details
Offering
Groq Compound
Offering detailsCustomPrice pending0 regions
Context Window: 131072 tokens; Input Modalities: text
GroqService details
Offering
GPT-OSS 120B on Groq
Offering detailsPay-as-you-go$0.150 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
GroqService details
Offering
GPT-OSS 20B on Groq
Offering detailsPay-as-you-go$0.075 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
GroqService details
Offering
Groq LPU AI Inference API
Offering detailsUsage-basedFree2 regions
Inference Speed: 500+ tokens/second; Latency: <1ms per token; +3 more
GroqService details
Offering
Groq LLaMA Inference
Offering detailsUsage-based$0.0001 per 1K input tokens (LLaMA 3 8B)1 region
Inference Speed: 750+ tokens/sec; Models Available: LLaMA 3, Mixtral, Gemma, Whisper; +3 more
GroqService details
Offering
Llama 3.1 8B Instant on Groq
Offering detailsPay-as-you-go$0.050 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
GroqService details
Offering
Llama 3.3 70B Versatile on Groq
Offering detailsPay-as-you-go$0.590 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
GroqService details
Offering
Llama 4 Scout on Groq
Offering detailsPay-as-you-go$0.110 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text, image
GroqService details
Offering
Groq Mixtral Inference
Offering detailsUsage-based$0.0002 per 1K input tokens1 region
Architecture: Mixture of Experts 8x7B; Speed: 500+ tokens/sec; +3 more
GroqService details
Offering
Qwen3 32B on Groq
Offering detailsPay-as-you-go$0.290 1M input tokens0 regions
Context Window: 131072 tokens; Input Modalities: text
H2O.aiService details
Offering
H2O.ai Model Deployment (Driverless AI + MLOps)
Offering detailsSubscriptionFree3 regions
Scoring: REST API + batch; Champion-Challenger: A/B traffic splitting; +2 more
Hailuo AIService details
Offering
Hailuo AI MiniMax API
Offering detailsUsage-based$0.0002 per 1K input tokens1 region
MiniMax-Text-01: 456B parameter model; Multimodal: Text, image, audio, video; +3 more
HeliconeService details
Offering
Helicone - AI Gateway and Observability
Offering detailsFreemiumFree1 region
Provider Support: OpenAI, Anthropic, Azure, Gemini, 30+; Request Logging: Full request/response capture; +3 more
Hugging FaceService details
Offering
Hugging Face Inference Endpoints
Offering detailsUsage-based$0.032 per hour (CPU)4 regions
One-Click Deployment: true; Auto-scaling: true; +3 more
HumanloopService details
Offering
Humanloop LLM Development Platform
Offering detailsFreemiumFree1 region
Prompt Management: true; Evaluation Framework: true; +3 more
HyperWriteService details
Offering
HyperWrite AI Models
Offering detailsSubscription$19.99 per month (Premium)1 region
Multi-Model Access: GPT-4, Claude, proprietary; Intelligent Routing: Auto model selection; +3 more
IBM CloudService details
Offering
IBM Cloud - Watson Machine Learning
Offering detailsUsage-basedFree5 regions
Model Serving: Online + batch scoring; AutoAI: Automated ML pipeline; +3 more
IBM ResearchService details
Offering
Granite 4.0 Micro
Offering detailsPay-as-you-go$0.017 1M input tokens0 regions
Context Window: 131000 tokens; Input Modalities: text
IBM watsonxService details
Offering
IBM watsonx.ai Foundation Models
Offering detailsUsage-based$0.0001 per 1K tokens (Granite 3B)5 regions
Granite Models: 3B–20B parameters; Prompt Engineering: true; +3 more
Inception LabsService details
Offering
Mercury
Offering detailsPay-as-you-go$0.250 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Inception LabsService details
Offering
Mercury 2
Offering detailsPay-as-you-go$0.250 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Inception LabsService details
Offering
Mercury Coder
Offering detailsPay-as-you-go$0.250 1M input tokens0 regions
Context Window: 128000 tokens; Input Modalities: text
Insilico MedicineService details
Offering
Insilico Medicine PandaOmics & Chemistry42
Offering detailsEnterpriseFree1 region
PandaOmics: AI target discovery; Chemistry42: Generative drug design; +3 more
Intel Gaudi (Habana Labs)Service details
Offering
Intel Gaudi AI Inference
Offering detailsUsage-based$13.11 per hour (AWS DL1 instance, dl1.24xlarge)2 regions
Hardware: Gaudi 1/2/3 HPU; SDK: Optimum Habana (PyTorch); +2 more
InvokeAIService details
Offering
InvokeAI - Generative AI API
Offering detailsOpen sourceFree1 region
Model Support: SD 1.x, SDXL, SD3; Workflows: Node-based pipeline editor; +2 more
JasperService details
Offering
Jasper AI Marketing Content Platform
Offering detailsSubscription$39 per month1 region
Brand Voice: true; Long-form Content: true; +3 more
KagiService details
Offering
Kagi - AI Search Summarization
Offering detailsSubscription$5 per month1 region
FastGPT: Instant AI answers; Universal Summarizer: Any URL summarization; +2 more
Khan AcademyService details
Offering
Khanmigo - AI Tutoring Assistant
Offering detailsSubscription$4 per month1 region
Socratic Tutoring: Question-based guidance; Subject Coverage: Math, science, humanities; +2 more
Kling AIService details
Offering
Kling AI - Video & Image Generation API
Offering detailsUsage-based$0.140 per video generation1 region
Video API: 5-10 second clips, 1080p; Async Processing: Job queue + webhooks; +2 more
LambdaService details
Offering
Lambda - GPU Cloud AI Inference
Offering detailsUsage-based$0.500 per hour (A10 GPU)5 regions
GPU Options: H100, A100, A10, V100; Persistent Storage: Attached storage volumes; +3 more
LanceDBService details
Offering
LanceDB RAG & AI Application Backend
Offering detailsFreemiumFree3 regions
RAG-Optimized Search: Hybrid ANN + BM25 retrieval; LangChain Integration: Native LangChain vector store; +3 more
LangChainService details
Offering
LangChain - AI Inference and LLM Integrations
Offering detailsOpen sourceFree1 region
LLM Integrations: 100+ providers; LCEL: Composable chain syntax; +3 more
Lepton AIService details
Offering
Lepton AI Inference & Deployment Platform
Offering detailsUsage-based$0.0003 per 1K tokens (Llama 3 8B)2 regions
Python SDK: true; OpenAI-Compatible API: true; +3 more
Lightning AIService details
Offering
Lightning AI Inference & Deployment
Offering detailsUsage-basedFree3 regions
PyTorch-Native Deployment: Lightning App + PyTorch Serve; Automatic Batching: Dynamic request batching; +3 more
Liquid AIService details
Offering
LFM2-24B-A2B
Offering detailsPay-as-you-go$0.030 1M input tokens0 regions
Context Window: 32768 tokens; Input Modalities: text
Liquid AIService details
Offering
LFM2.5-1.2B-Instruct
Offering detailsFreePrice pending0 regions
Context Window: 32768 tokens; Input Modalities: text
| Service | Offering | Pricing model | Starting price | Regions | Features | Links |
|---|---|---|---|---|---|---|
Google GeminiService details | Gemma 3 4B Offering details | Pay-as-you-go | $0.040 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text, image | |
Google GeminiService details | Gemma 3 4B Offering details | Free | — | 0 | Context Window: 32768 tokens; Input Modalities: text, image | |
Google GeminiService details | Gemma 3n 2B Offering details | Free | — | 0 | Context Window: 8192 tokens; Input Modalities: text | |
Google GeminiService details | Gemma 3n 4B Offering details | Pay-as-you-go | $0.020 1M input tokens | 0 | Context Window: 32768 tokens; Input Modalities: text | |
Google GeminiService details | Gemma 3n 4B Offering details | Free | — | 0 | Context Window: 8192 tokens; Input Modalities: text | |
Google GeminiService details | Gemma 4 26B A4B Offering details | Pay-as-you-go | $0.130 1M input tokens | 0 | Context Window: 262144 tokens; Input Modalities: image, text, video | |
Google GeminiService details | Gemma 4 31B Offering details | Pay-as-you-go | $0.140 1M input tokens | 0 | Context Window: 262144 tokens; Input Modalities: image, text, video | |
Google GeminiService details | Lyria 3 Clip Preview Offering details | Free | — | 0 | Context Window: 1048576 tokens; Input Modalities: text, image | |
Google GeminiService details | Lyria 3 Pro Preview Offering details | Free | — | 0 | Context Window: 1048576 tokens; Input Modalities: text, image | |
Google WorkspaceService details | Gemini for Google Workspace Offering details | Subscription | $20 per user/month (Gemini Business add-on) | 1 | Gmail AI: Draft, summarize, reply; Docs AI: Write, rewrite, proofread; +2 more | |
GrammarlyService details | Grammarly AI Writing Assistant Offering details | Freemium | Free | 1 | Real-time Suggestions: true; Generative AI Writing: true; +3 more | |
GrammarlyService details | Grammarly Business Offering details | Subscription | $15 per member/month (billed annually, minimum 3 seats) | 1 | Style Guide: Company style guide enforcement; Brand Tone: Custom tone settings; +2 more | |
GrammarlyService details | Grammarly GO (AI Writing Features) Offering details | Subscription | $12 per month (Pro plan, billed annually) | 1 | Generation: Draft emails and documents; Rewriting: Full-paragraph rewrites; +2 more | |
GraphcoreService details | Graphcore Poplar SDK Offering details | Free | Free | 1 | Compiler: Poplar Graph Compiler; PyTorch Integration: PopTorch; +2 more | |
GroqService details | Groq Compound Offering details | Custom | — | 0 | Context Window: 131072 tokens; Input Modalities: text | |
GroqService details | GPT-OSS 120B on Groq Offering details | Pay-as-you-go | $0.150 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
GroqService details | GPT-OSS 20B on Groq Offering details | Pay-as-you-go | $0.075 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
GroqService details | Groq LPU AI Inference API Offering details | Usage-based | Free | 2 | Inference Speed: 500+ tokens/second; Latency: <1ms per token; +3 more | |
GroqService details | Groq LLaMA Inference Offering details | Usage-based | $0.0001 per 1K input tokens (LLaMA 3 8B) | 1 | Inference Speed: 750+ tokens/sec; Models Available: LLaMA 3, Mixtral, Gemma, Whisper; +3 more | |
GroqService details | Llama 3.1 8B Instant on Groq Offering details | Pay-as-you-go | $0.050 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
GroqService details | Llama 3.3 70B Versatile on Groq Offering details | Pay-as-you-go | $0.590 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
GroqService details | Llama 4 Scout on Groq Offering details | Pay-as-you-go | $0.110 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text, image | |
GroqService details | Groq Mixtral Inference Offering details | Usage-based | $0.0002 per 1K input tokens | 1 | Architecture: Mixture of Experts 8x7B; Speed: 500+ tokens/sec; +3 more | |
GroqService details | Qwen3 32B on Groq Offering details | Pay-as-you-go | $0.290 1M input tokens | 0 | Context Window: 131072 tokens; Input Modalities: text | |
H2O.aiService details | H2O.ai Model Deployment (Driverless AI + MLOps) Offering details | Subscription | Free | 3 | Scoring: REST API + batch; Champion-Challenger: A/B traffic splitting; +2 more | |
Hailuo AIService details | Hailuo AI MiniMax API Offering details | Usage-based | $0.0002 per 1K input tokens | 1 | MiniMax-Text-01: 456B parameter model; Multimodal: Text, image, audio, video; +3 more | |
HeliconeService details | Helicone - AI Gateway and Observability Offering details | Freemium | Free | 1 | Provider Support: OpenAI, Anthropic, Azure, Gemini, 30+; Request Logging: Full request/response capture; +3 more | |
Hugging FaceService details | Hugging Face Inference Endpoints Offering details | Usage-based | $0.032 per hour (CPU) | 4 | One-Click Deployment: true; Auto-scaling: true; +3 more | |
HumanloopService details | Humanloop LLM Development Platform Offering details | Freemium | Free | 1 | Prompt Management: true; Evaluation Framework: true; +3 more | |
HyperWriteService details | HyperWrite AI Models Offering details | Subscription | $19.99 per month (Premium) | 1 | Multi-Model Access: GPT-4, Claude, proprietary; Intelligent Routing: Auto model selection; +3 more | |
IBM CloudService details | IBM Cloud - Watson Machine Learning Offering details | Usage-based | Free | 5 | Model Serving: Online + batch scoring; AutoAI: Automated ML pipeline; +3 more | |
IBM ResearchService details | Granite 4.0 Micro Offering details | Pay-as-you-go | $0.017 1M input tokens | 0 | Context Window: 131000 tokens; Input Modalities: text | |
IBM watsonxService details | IBM watsonx.ai Foundation Models Offering details | Usage-based | $0.0001 per 1K tokens (Granite 3B) | 5 | Granite Models: 3B–20B parameters; Prompt Engineering: true; +3 more | |
Inception LabsService details | Mercury Offering details | Pay-as-you-go | $0.250 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Inception LabsService details | Mercury 2 Offering details | Pay-as-you-go | $0.250 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Inception LabsService details | Mercury Coder Offering details | Pay-as-you-go | $0.250 1M input tokens | 0 | Context Window: 128000 tokens; Input Modalities: text | |
Insilico MedicineService details | Insilico Medicine PandaOmics & Chemistry42 Offering details | Enterprise | Free | 1 | PandaOmics: AI target discovery; Chemistry42: Generative drug design; +3 more | |
Intel Gaudi (Habana Labs)Service details | Intel Gaudi AI Inference Offering details | Usage-based | $13.11 per hour (AWS DL1 instance, dl1.24xlarge) | 2 | Hardware: Gaudi 1/2/3 HPU; SDK: Optimum Habana (PyTorch); +2 more | |
InvokeAIService details | InvokeAI - Generative AI API Offering details | Open source | Free | 1 | Model Support: SD 1.x, SDXL, SD3; Workflows: Node-based pipeline editor; +2 more | |
JasperService details | Jasper AI Marketing Content Platform Offering details | Subscription | $39 per month | 1 | Brand Voice: true; Long-form Content: true; +3 more | |
KagiService details | Kagi - AI Search Summarization Offering details | Subscription | $5 per month | 1 | FastGPT: Instant AI answers; Universal Summarizer: Any URL summarization; +2 more | |
Khan AcademyService details | Khanmigo - AI Tutoring Assistant Offering details | Subscription | $4 per month | 1 | Socratic Tutoring: Question-based guidance; Subject Coverage: Math, science, humanities; +2 more | |
Kling AIService details | Kling AI - Video & Image Generation API Offering details | Usage-based | $0.140 per video generation | 1 | Video API: 5-10 second clips, 1080p; Async Processing: Job queue + webhooks; +2 more | |
LambdaService details | Lambda - GPU Cloud AI Inference Offering details | Usage-based | $0.500 per hour (A10 GPU) | 5 | GPU Options: H100, A100, A10, V100; Persistent Storage: Attached storage volumes; +3 more | |
LanceDBService details | LanceDB RAG & AI Application Backend Offering details | Freemium | Free | 3 | RAG-Optimized Search: Hybrid ANN + BM25 retrieval; LangChain Integration: Native LangChain vector store; +3 more | |
LangChainService details | LangChain - AI Inference and LLM Integrations Offering details | Open source | Free | 1 | LLM Integrations: 100+ providers; LCEL: Composable chain syntax; +3 more | |
Lepton AIService details | Lepton AI Inference & Deployment Platform Offering details | Usage-based | $0.0003 per 1K tokens (Llama 3 8B) | 2 | Python SDK: true; OpenAI-Compatible API: true; +3 more | |
Lightning AIService details | Lightning AI Inference & Deployment Offering details | Usage-based | Free | 3 | PyTorch-Native Deployment: Lightning App + PyTorch Serve; Automatic Batching: Dynamic request batching; +3 more | |
Liquid AIService details | LFM2-24B-A2B Offering details | Pay-as-you-go | $0.030 1M input tokens | 0 | Context Window: 32768 tokens; Input Modalities: text | |
Liquid AIService details | LFM2.5-1.2B-Instruct Offering details | Free | — | 0 | Context Window: 32768 tokens; Input Modalities: text |
Showing 151–200 of 515 offerings