Anyscale
Commercial platform built on Ray — distributed training, fine-tuning, serving. Anyscale Endpoints provides hosted OSS inference; ray cluster is the substrate underneath OpenAI's training stack.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 22 cited facts, 2 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Ray-based AI platform vendor fix
- Tier
- T1
- Section
- Inference platforms & gateways
- Latest release
- v0.26.112 (2026-10-20) — anyscale registry fix
- License
- proprietary; Ray Apache-2.0 repo fix
- Pricing
- Pay-as-you-go compute billed in Anyscale credits per hour (e.g. A100 ~4.96 AC/hr); $100 free credit for new users; committed contracts with volume discounts via sales vendor fix
- Funding
- $259M total raised through Series C 2021-12 ($99M, Addition led; $1B valuation). third-party fix
- Freshness
- 2026-10-27 fix
- Layer
- model-infra repo fix
- Licensing
- commercial repo fix
- Protocols
- openai-compatible vendor fix
- Compliance
- iso27001, soc2-type2 vendor fix
- Developer activity
- OpenRank 111.42 (12-mo avg 164.68) · 285 participants — 2026-09 third-party fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
$99M Series C 2021 at $1B; founded by Ray creators at UC Berkeley.
Technical surface
- API surface
- searched not found
- Backend storage
- not applicable — not a memory product
- Deployment
- Both (self-hosted + managed cloud) — Anyscale-hosted, or BYOC in your own cloud/VPC/on-prem (VMs or Kubernetes)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other inference platforms & gateways in the catalog, ranked by inbound references.
- LiteLLM T1
BerriAI's open-source LLM gateway — unified OpenAI-format API for 100+ providers; LiteLLM Proxy adds budgets, fallbacks, observability, rate-limiting.
- OpenRouter T1
Unified API + marketplace for 300+ models — pay-as-you-go credits, automatic fallback, model arena. Used as default LLM router by many JS/TS agents.
- Together AI T1
Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated endpoints, fine-tuning API, training cluster.
- Fireworks AI T1
Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-LoRA serving. Targets latency-sensitive production use cases.
- vLLM T1
Open-source LLM inference engine with PagedAttention — high-throughput batching, paged KV-cache. UC Berkeley origin; de-facto OSS inference stack.
- Portkey AI T2
AI gateway + observability — load balancing across 200+ LLMs, retries, caching, eval, prompts. Open-source Gateway + commercial Portkey Cloud. Acquired by Palo Alto Networks (closed about 2026-06); now sold as Prisma AIRS AI Gateway (GA 2026-07-16).
Sources (21 cited facts, 2 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Ray-based AI platform vendor
- What it does & what's distinct Commercial platform built on Ray — distributed training, fine-tuning, serving. Anyscale … vendor
- Claims / benefits $99M Series C 2021 at $1B; founded by Ray creators at UC Berkeley. vendor
- Created 2019 vendor
- Latest release v0.26.112 (2026-10-20) — anyscale registry
- License proprietary; Ray Apache-2.0 repo
- GitHub ray-project/ray — ~44.1k stars, last commit 2026-10 repo
- Funding $259M total raised through Series C 2021-12 ($99M, Addition led; $1B valuation). third-party
- Customers / scale OpenAI (Ray for ChatGPT training), Cohere, Pinterest, Spotify, Uber, Shopify, Instacart,… vendor
- Pricing Pay-as-you-go compute billed in Anyscale credits per hour (e.g. A100 ~4.96 AC/hr); $100 … vendor
- Deployment Both (self-hosted + managed cloud) — Anyscale-hosted, or BYOC in your own cloud/VPC/on-p… vendor
- HQ San Francisco, CA, USA. vendor
- Founders / pedigree Robert Nishihara, Philipp Moritz, Ion Stoica (CEO; UC Berkeley, ex-Databricks co-founder… vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup model-infra repo
- developer-activity-opendigger {"activity":886.59,"as_of":"2026-09","openrank_12mo":164.68,"openrank_current":111.42,"p… third-party
- compliance-certifications iso27001,soc2-type2 vendor
- sdk-languages python vendor
- protocol-support openai-compatible vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-27
- License first recorded as “proprietary; Ray Apache-2.0” source
- Latest release first recorded as “v0.26.112 (2026-10-20) — anyscale” source
- Pricing first recorded as “Pay-as-you-go compute billed in Anyscale credits per hour (e.g. A100 ~4.96 AC/hr); $100 free credit for new users; committed contracts with volume discounts via sales” source
- Deployment first recorded as “Both (self-hosted + managed cloud) — Anyscale-hosted, or BYOC in your own cloud/VPC/on-prem (VMs or Kubernetes)” source
Related systems
Referenced by (5)
- LiteLLM integrates with — LiteLLM docs have an Anyscale provider page. (verified 2026-10-29)
- LlamaIndex (framework) integrates with — LlamaIndex has an official LLM integration package llama-index-llms-anyscale in its repo. (verified 2026-10-29)
- Portkey AI integrates with — Portkey docs have an Anyscale LLM provider integration page. (verified 2026-10-29)
- Vapi integrates with — Vapi docs list Anyscale as a provider/integration. (verified 2026-10-29)
- Weaviate integrates with — Weaviate's integrations / model-provider docs list Anyscale as an integration. (verified 2026-10-29)