losclouds
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.

A
AI21 LabsService details

Offering

AI21 Labs Jamba & Jurassic API

Offering details
Usage-based$0.0002 per 1K tokens1 region

Context Window: 256K tokens; Hybrid Architecture: SSM + Transformer; +2 more

A
AI21 LabsService details

Offering

Jamba 1.5 Large

Offering details
Pay-as-you-go$2 1M input tokens0 regions

Context Window: 256000 tokens; Input Modalities: text

A
AI21 LabsService details

Offering

Jamba 1.5 Mini

Offering details
Pay-as-you-go$0.200 1M input tokens0 regions

Context Window: 256000 tokens; Input Modalities: text

A
AI21 LabsService details

Offering

Jamba Large 1.7

Offering details
Pay-as-you-go$2 1M input tokens0 regions

Context Window: 256000 tokens; Input Modalities: text

A
Aleph AlphaService details

Offering

Aleph Alpha Luminous & Pharia API

Offering details
Usage-based$0.030 per 1K tokens1 region

European Data Residency: Germany; Explainability: true; +2 more

A
Algolia AIService details

Offering

Algolia AI NeuralSearch

Offering details
Usage-basedFree1 region

Neural Search: Hybrid keyword + vector; Inference: Managed embeddings; +3 more

A
AmazonService details

Offering

Nova 2 Lite

Offering details
Pay-as-you-go$0.300 1M input tokens0 regions

Context Window: 1000000 tokens; Input Modalities: text, image, video, file

A
AmazonService details

Offering

Amazon Nova Lite

Offering details
Pay-as-you-go$0.060 1M input tokens0 regions

Context Window: 300000 tokens; Input Modalities: text, image, video

A
AmazonService details

Offering

Nova Lite 1.0

Offering details
Pay-as-you-go$0.060 1M input tokens0 regions

Context Window: 300000 tokens; Input Modalities: text, image

A
AmazonService details

Offering

Amazon Nova Micro

Offering details
Pay-as-you-go$0.035 1M input tokens0 regions

Context Window: 128000 tokens; Input Modalities: text

A
AmazonService details

Offering

Nova Micro 1.0

Offering details
Pay-as-you-go$0.035 1M input tokens0 regions

Context Window: 128000 tokens; Input Modalities: text

A
AmazonService details

Offering

Nova Premier 1.0

Offering details
Pay-as-you-go$2.50 1M input tokens0 regions

Context Window: 1000000 tokens; Input Modalities: text, image

A
AmazonService details

Offering

Amazon Nova Pro

Offering details
Pay-as-you-go$0.800 1M input tokens0 regions

Context Window: 300000 tokens; Input Modalities: text, image, video

A
AmazonService details

Offering

Nova Pro 1.0

Offering details
Pay-as-you-go$0.800 1M input tokens0 regions

Context Window: 300000 tokens; Input Modalities: text, image

A
Amazon Web ServicesService details

Offering

Amazon Bedrock Foundation Model API

Offering details
Usage-based$0.0003 per 1K input tokens5 regions

Multi-Model Access: 30+ models; Bedrock Agents: true; +3 more

A
Amazon Web ServicesService details

Offering

Amazon SageMaker ML Platform

Offering details
Usage-based$0.046 per hour (ml.t2.medium instance)5 regions

JumpStart Foundation Models: true; AutoML: true; +3 more

A
AMDService details

Offering

AMD ROCm AI Platform

Offering details
FreeFree1 region

Frameworks: PyTorch, TensorFlow, JAX; GPU Series: Instinct MI300X; +2 more

A
AnthropicService details

Offering

Claude 3.5 Haiku

Offering details
Pay-as-you-go$0.800 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude 3.5 Sonnet

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude 3.7 Sonnet

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude 3.7 Sonnet (thinking)

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image, file

A
AnthropicService details

Offering

Claude 3 Haiku

Offering details
Pay-as-you-go$0.250 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude 3 Opus

Offering details
Pay-as-you-go$15 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude for Enterprise

Offering details
SubscriptionFree3 regions

Model Access: All Claude models; Data Privacy: No training on data; +2 more

A
AnthropicService details

Offering

Claude Haiku

Offering details
Usage-based$0.001 per 1K input tokens3 regions

Context Window: 200K tokens; Input Pricing: $0.001/1K tokens; +3 more

A
AnthropicService details

Offering

Claude Haiku 4.5

Offering details
Pay-as-you-go$1 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude Opus

Offering details
Usage-based$0.005 per 1K input tokens3 regions

Context Window: 200K tokens; Input Pricing: $0.005/1K tokens; +3 more

A
AnthropicService details

Offering

Claude Opus 4

Offering details
Pay-as-you-go$15 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: image, text, file

A
AnthropicService details

Offering

Claude Opus 4.1

Offering details
Pay-as-you-go$15 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: image, text, file

A
AnthropicService details

Offering

Claude Opus 4.5

Offering details
Pay-as-you-go$5 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: file, image, text

A
AnthropicService details

Offering

Claude Opus 4.6

Offering details
Pay-as-you-go$5 1M input tokens0 regions

Context Window: 1000000 tokens; Input Modalities: text, image

A
AnthropicService details

Offering

Claude Sonnet

Offering details
Usage-based$0.003 per 1K input tokens3 regions

Context Window: 200K tokens; Input Pricing: $0.003/1K tokens; +3 more

A
AnthropicService details

Offering

Claude Sonnet 4

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 200000 tokens; Input Modalities: image, text, file

A
AnthropicService details

Offering

Claude Sonnet 4.5

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 1000000 tokens; Input Modalities: text, image, file

A
AnthropicService details

Offering

Claude Sonnet 4.6

Offering details
Pay-as-you-go$3 1M input tokens0 regions

Context Window: 1000000 tokens; Input Modalities: text, image

A
AnyscaleService details

Offering

Anyscale Endpoints & Ray Platform

Offering details
Usage-based$0.0002 per 1K tokens3 regions

Ray Integration: true; OpenAI Compatible API: true; +2 more

S
Apache SolrService details

Offering

Apache Solr Neural Search

Offering details
Open sourceFree2 regions

Dense Vector Search: kNN with HNSW index; Hybrid Search: BM25 + vector combined; +3 more

A
Arcee AIService details

Offering

Coder Large

Offering details
Pay-as-you-go$0.500 1M input tokens0 regions

Context Window: 32768 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Maestro Reasoning

Offering details
Pay-as-you-go$0.900 1M input tokens0 regions

Context Window: 131072 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Spotlight

Offering details
Pay-as-you-go$0.180 1M input tokens0 regions

Context Window: 131072 tokens; Input Modalities: image, text

A
Arcee AIService details

Offering

Trinity Large Preview

Offering details
FreePrice pending0 regions

Context Window: 131000 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Trinity Large Thinking

Offering details
Pay-as-you-go$0.220 1M input tokens0 regions

Context Window: 262144 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Trinity Mini

Offering details
Pay-as-you-go$0.045 1M input tokens0 regions

Context Window: 131072 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Trinity Mini

Offering details
FreePrice pending0 regions

Context Window: 131072 tokens; Input Modalities: text

A
Arcee AIService details

Offering

Virtuoso Large

Offering details
Pay-as-you-go$0.750 1M input tokens0 regions

Context Window: 131072 tokens; Input Modalities: text

A
AssemblyAIService details

Offering

AssemblyAI Speech AI Inference

Offering details
Usage-based$0.370 per audio hour1 region

Model: Universal-2; Real-Time Streaming: WebSocket API; +3 more

B
BaiduService details

Offering

ERNIE 4.5 21B A3B

Offering details
Pay-as-you-go$0.070 1M input tokens0 regions

Context Window: 120000 tokens; Input Modalities: text

Showing 1–50 of 515 offerings