{"origin":{"source":"Infrabase.ai","url":"https://infrabase.ai","license":"CC-BY-4.0","note":"Directory data maintained by hand at infrabase.ai. Attribution required.","docs":"https://infrabase.ai/api/query/docs"},"count":20,"total":104,"next_offset":20,"results":[{"name":"2kw.ai","slug":"2kw-ai","infrabase_url":"https://infrabase.ai/inference-apis/2kw-ai","site_url":"https://2kw.ai","tagline":"EU-hosted AI integration platform combining a provider gateway, document extraction, evals and cost observability","primary_job":"llm-gateway","secondary_jobs":["llm-observability"],"categories":["inference-apis"],"pricing":"Monthly subscriptions","hq_country":"DE","gdpr":true,"github_stars":null,"updated_at":"2026-09-24T08:48:57Z"},{"name":"AI Gateway HQ","slug":"ai-gateway-hq","infrabase_url":"https://infrabase.ai/inference-apis/ai-gateway-hq","site_url":"https://aigatewayhq.com","tagline":"LLM gateway built around spend limits enforced before a request reaches a provider","primary_job":"llm-gateway","secondary_jobs":["llm-observability"],"categories":["inference-apis"],"pricing":null,"hq_country":"US","gdpr":null,"github_stars":null,"updated_at":"2026-09-17T08:14:16Z"},{"name":"AiQu","slug":"aiqu","infrabase_url":"https://infrabase.ai/inference-apis/aiqu","site_url":"https://aiqu.ai","tagline":"Swedish GPU infrastructure and LLM hosting platform with API-first deployment, no Kubernetes required","primary_job":"gpu-compute","secondary_jobs":["hosted-inference-api"],"categories":["inference-apis"],"pricing":"Monthly subscriptions","hq_country":"SE","gdpr":true,"github_stars":null,"updated_at":"2026-05-26T13:40:45Z"},{"name":"Airon","slug":"airon","infrabase_url":"https://infrabase.ai/inference-apis/airon","site_url":"https://airon.ai","tagline":"Dedicated bare-metal GPU infrastructure for AI workloads, hosted in Nordic datacenters","primary_job":"gpu-compute","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Hourly","hq_country":"SE","gdpr":true,"github_stars":null,"updated_at":"2026-09-24T08:49:15Z"},{"name":"AISIX","slug":"aisix","infrabase_url":"https://infrabase.ai/inference-apis/aisix","site_url":"https://api7.ai/ai-gateway","tagline":"Open-source AI gateway in Rust with one OpenAI-compatible API across 100+ LLM providers","primary_job":"llm-gateway","secondary_jobs":["llm-observability"],"categories":["inference-apis"],"pricing":"Monthly subscriptions","hq_country":null,"gdpr":null,"github_stars":null,"updated_at":"2026-09-24T08:48:57Z"},{"name":"AKI.IO","slug":"aki-io","infrabase_url":"https://infrabase.ai/inference-apis/aki-io","site_url":"https://aki.io","tagline":"European AI API for open-source models on EU infrastructure","primary_job":"gpu-compute","secondary_jobs":["hosted-inference-api"],"categories":["inference-apis"],"pricing":"10 EUR free credits, then pay-per-token","hq_country":"DE","gdpr":null,"github_stars":null,"updated_at":"2026-09-24T08:49:15Z"},{"name":"Akumi","slug":"akumi","infrabase_url":"https://infrabase.ai/inference-apis/akumi","site_url":"https://akumi.eu/","tagline":"EU-hosted OpenAI-compatible inference API with data residency, PII pseudonymization and per-request audit trails","primary_job":"hosted-inference-api","secondary_jobs":["llm-gateway","llm-guardrails"],"categories":["inference-apis"],"pricing":"Monthly subscriptions","hq_country":"NL","gdpr":true,"github_stars":null,"updated_at":"2026-09-24T08:49:18Z"},{"name":"Alibaba Cloud Model Studio","slug":"alibaba-cloud-model-studio","infrabase_url":"https://infrabase.ai/inference-apis/alibaba-cloud-model-studio","site_url":"https://www.alibabacloud.com/en/product/modelstudio","tagline":"Hosted API access to Qwen and third-party models across six global regions","primary_job":"hosted-inference-api","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Per token usage","hq_country":null,"gdpr":null,"github_stars":null,"updated_at":"2026-08-23T07:18:55Z"},{"name":"Amazon Bedrock","slug":"amazon-bedrock","infrabase_url":"https://infrabase.ai/inference-apis/amazon-bedrock","site_url":"https://aws.amazon.com/bedrock/","tagline":"Managed API access to foundation models on AWS with built-in fine-tuning and agent tooling","primary_job":"hosted-inference-api","secondary_jobs":["fine-tuning-platform"],"categories":["inference-apis"],"pricing":"Per token usage","hq_country":"US","gdpr":true,"github_stars":null,"updated_at":"2026-05-26T13:40:45Z"},{"name":"Anthropic Claude","slug":"anthropic-claude","infrabase_url":"https://infrabase.ai/inference-apis/anthropic-claude","site_url":"https://claude.ai/","tagline":"Claude API for building AI applications with Opus, Sonnet, and Haiku models","primary_job":"hosted-inference-api","secondary_jobs":["agent-platform"],"categories":["inference-apis"],"pricing":"Per token usage","hq_country":"US","gdpr":true,"github_stars":3523,"updated_at":"2026-05-26T13:40:43Z"},{"name":"Anyscale","slug":"anyscale","infrabase_url":"https://infrabase.ai/inference-apis/anyscale","site_url":"https://www.anyscale.com/","tagline":"Fast, cost-efficient, serverless APIs for LLM Serving and Fine Tuning","primary_job":"hosted-inference-api","secondary_jobs":["fine-tuning-platform","serverless-gpu-platform"],"categories":["inference-apis"],"pricing":"Pay-as-you-go","hq_country":"US","gdpr":null,"github_stars":null,"updated_at":"2026-05-26T13:40:43Z"},{"name":"ARK Labs","slug":"ark-labs","infrabase_url":"https://infrabase.ai/inference-apis/ark-labs","site_url":"https://ark-labs.cloud","tagline":"Sovereign AI inference infrastructure for regulated EU environments, with heterogeneous GPU support","primary_job":"gpu-compute","secondary_jobs":["hosted-inference-api"],"categories":["inference-apis"],"pricing":"Pay-as-you-go","hq_country":null,"gdpr":null,"github_stars":null,"updated_at":"2026-09-24T08:44:22Z"},{"name":"Aurora Inference","slug":"aurora-inference","infrabase_url":"https://infrabase.ai/inference-apis/aurora-inference","site_url":"https://aurorainfra.ai/products/inference","tagline":"OpenAI-compatible API for open-weight models, with in-region deployment on reserved capacity","primary_job":"hosted-inference-api","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Per token usage","hq_country":"PL","gdpr":null,"github_stars":null,"updated_at":"2026-09-23T19:51:10Z"},{"name":"Baseten","slug":"baseten","infrabase_url":"https://infrabase.ai/inference-apis/baseten","site_url":"https://www.baseten.co","tagline":"AI inference platform for deploying and serving ML models with autoscaling and optimized infrastructure","primary_job":"serverless-gpu-platform","secondary_jobs":["hosted-inference-api"],"categories":["inference-apis"],"pricing":"Usage-based","hq_country":"US","gdpr":null,"github_stars":1155,"updated_at":"2026-05-26T13:40:44Z"},{"name":"Beam","slug":"beam","infrabase_url":"https://infrabase.ai/inference-apis/beam","site_url":"https://www.beam.cloud","tagline":"Open-source serverless GPU cloud with sub-second cold starts and auto-scaling","primary_job":"serverless-gpu-platform","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Pay-as-you-go","hq_country":"US","gdpr":null,"github_stars":1654,"updated_at":"2026-05-26T13:40:44Z"},{"name":"BentoML","slug":"bentoml","infrabase_url":"https://infrabase.ai/inference-apis/bentoml","site_url":"https://bentoml.com/","tagline":"BentoML is the platform for software engineers to build AI products.","primary_job":"serverless-gpu-platform","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Pay-as-you-go","hq_country":"US","gdpr":null,"github_stars":null,"updated_at":"2026-09-24T08:48:57Z"},{"name":"Berget AI","slug":"berget-ai","infrabase_url":"https://infrabase.ai/inference-apis/berget-ai","site_url":"https://berget.ai","tagline":"EU-sovereign AI inference platform with OpenAI-compatible API","primary_job":"hosted-inference-api","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Free tier with €5 credits. Starter €25/mo, Team €50/mo, Enterprise €500/mo.","hq_country":"SE","gdpr":true,"github_stars":1,"updated_at":"2026-05-26T13:40:44Z"},{"name":"Cerebras","slug":"cerebras","infrabase_url":"https://infrabase.ai/inference-apis/cerebras","site_url":"https://cerebras.ai","tagline":"Ultra-fast inference on custom wafer-scale hardware with OpenAI-compatible API","primary_job":"hosted-inference-api","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Per token usage","hq_country":"US","gdpr":null,"github_stars":1165,"updated_at":"2026-05-26T13:40:44Z"},{"name":"Cerebrium","slug":"cerebrium","infrabase_url":"https://infrabase.ai/inference-apis/cerebrium","site_url":"https://www.cerebrium.ai","tagline":"Serverless GPU infrastructure for deploying AI models with sub-5 second cold starts","primary_job":"serverless-gpu-platform","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Pay-per-second","hq_country":"US","gdpr":null,"github_stars":null,"updated_at":"2026-05-26T13:40:43Z"},{"name":"CheapestInference","slug":"cheapestinference","infrabase_url":"https://infrabase.ai/inference-apis/cheapestinference","site_url":"https://cheapestinference.com","tagline":"Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows","primary_job":"hosted-inference-api","secondary_jobs":[],"categories":["inference-apis"],"pricing":"Monthly subscriptions","hq_country":null,"gdpr":null,"github_stars":null,"updated_at":"2026-09-24T08:57:32Z"}]}