Cerebrium

HostedInference cloud

Real-time AI infrastructure that scales with you

Homepage Docs Pricing Repository

Scanned 14 Oct 2026 · Schema v5 · features v21

From: $100/mo
Per-second compute (GPU + vCPU + memory) + plan tier (concurrency/seats); storage GB-month
Free tier: Yes
Card requirement unconfirmed.
Isolation: Kata / gVisor
hardened or user-space kernel
Regions: 4
N. Virginia · Kansas City (Nebius) · Stockholm · Finland (Nebius)
Capabilities: 18 / 61
6 partial · 37 fail · 0 not assessed
Agent readiness: 11/11 · 9/11
read · drive, pre-login surface

Advertised for

Real time inference · Voice agents · LLM inference · Video models · Custom python servers · Batch training

Built for

Developers, then technical

· CLI-first quickstart, cerebrium.toml and container images — https://cerebrium.ai/docs/getting-started/introduction.md
· Usage-priced GPU/CPU/memory seconds — https://cerebrium.ai/pricing

01 Pricing Per-second compute (GPU + vCPU + memory) + plan tier (concurrency/seats); storage GB-month

Tier	EntryHobby	Standard	TopEnterprise
Price	Free + compute	$100/mo + compute	Custom
Includes	3 seats; up to 3 apps; 500 containers + 5 concurrent GPUs; logs conflict (1 vs 7 days); first 100 GB storage free.	Unlimited apps; 1000 containers + 30 concurrent GPUs; custom domains; 30-day logs; seats conflict (unlimited vs 10).	unlimited GPU concurrency · dedicated Slack · white-glove onboarding · ML engineering services · unlimited log retention · HIPAA/GDPR/ISO 27001
Storage	100 GB	100 GB	—
GPU hours overage	$3.3984/h	$3.3984/h	—
Storage overage	$0.05/GB	$0.05/GB	—
vCPU hours overage	$0.02358/h	$0.02358/h	—
Memory gb hours overage	$0.007992/h	$0.007992/h	—

GPU-second (by type) + vCPU-second + GB-RAM-second; storage GB-month·Card required: unconfirmed·cerebrium.ai

Overages: Per-second GPU $0.000164/s (T4) → $0.00167/s (B200); CPU $0.00000655/vCPU/s; memory $0.00000222/GB/s; storage $0.05/GB-mo (100 GB free)

02 Website design Desktop public website · assessed 14 Oct 2026

Complete assessment.

Dark purple/pink expressive marketing contrasts with pale structured pricing and a light three-column documentation surface. Desktop viewport only; consent overlays partly obscure marketing copy.

Corporate

Landing page: captured
Pricing: captured
Docs: captured

03 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Kata / gVisorhardened or user-space kernel

Persistence

Region-local /persistent-storage; global apps additionally mount /global-persistent-storage. Files are not automatically synchronized between regional volumes.

Snapshots / forks

Yes

Resources & limits

Storage

Persistent project volumes per region; shared global volume for global apps; first 100 GB storage free, then $0.05/GB-month.

Limits & quotas

Hobby: 3 apps, 3 seats, 500 containers / 5 concurrent GPUs. Standard: unlimited apps, 1000 containers / 30 GPUs. Pricing contradicts itself on Standard seats (unlimited vs 10) and Hobby logs (1 vs 7 days).

GPU

Yes

Access

Deploy interface

cliapidockerfilecontainer-imagegit-push

SDK languages

None

Network & secrets

Egress controls

Secrets

Encrypted project/app secrets exposed as environment variables; API and CLI management.

Bring your own cloud

Placement & use

Jurisdiction

AWS and Nebius regions in US and Europe; additional regions available on request. Placement supports global, US/EU zones or specific region.

Advertised workloads

Real time inferenceVoice agentsLLM inferenceVideo modelsCustom python serversBatch training

04 Capabilities 18 pass · 6 partial · 37 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 4/11

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not supported

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Partially supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Partially supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Supported

GPU computeGPU-backed instances available.

Supported

Multi-regionCompute placeable in more than one geographic region.

Partially supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not supported

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 4/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Supported

Custom domainsBring-your-own domain via CNAME/DNS.

Supported

Public preview URLsShareable per-deploy / per-branch URLs.

Partially supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not supported

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Not supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Supported

Email send / receiveSend and/or receive email from the workload.

Not supported

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not supported

Developer access 4/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Not supported

SSH accessDirect SSH into workloads.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Partially supported

Git deployDeploy from a Git repo / push-to-deploy.

Supported

Private container registryHosted private image registry.

Not supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not supported

AI & agents 3/12

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Not supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Supported

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not supported

Data 0/4

First-party databasePlatform-provided managed database.

Not supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not supported

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not supported

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not supported

Platform & operations 1/6

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not supported

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not supported

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not supported

Organisation & security 2/9

Built-in authPlatform-provided authentication / IAM for workloads.

Partially supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

SharingShare a running workload/resource via link (optionally gated).

Not supported

BYOCRuns inside the customer's own cloud account.

Not supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Not supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Deploy your own model weights as an autoscaling inference endpointbyo-model-deployment
“Serve OpenAI GPT-OSS open weight models with vLLM on Cerebrium” cerebrium.ai

05 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

11/11

9 full · 2 partial · 100% of applicable checks

llms.txt
Supported
“https://cerebrium.ai/docs/llms.txt — Substantive docs and apex indexes with operational pages and pricing links.”
llms-full.txt
Supported
“https://cerebrium.ai/docs/llms-full.txt — 405925-byte comprehensive Markdown document fetched; apex variant 404 but docs copy exists.”
robots.txt AI policy
Supported
“https://cerebrium.ai/robots.txt — Explicit AI crawler allow rules.”
JSON-LD
Supported
“https://cerebrium.ai/ — Organization, WebSite and SoftwareApplication with offers.”
Sitemap
Supported
“https://cerebrium.ai/sitemap.xml — Nontrivial XML urlset.”
Meta tags
Supported
“https://cerebrium.ai/ — Descriptive title, description, OG and Twitter metadata.”
Markdown negotiation
Partially supported
“https://cerebrium.ai/docs/getting-started/introduction.md — Homepage Accept: text/markdown still HTML; documentation .md URLs serve clean Markdown.”
Content efficiency
Partially supported
“https://cerebrium.ai/ — 7985 extracted readable-text bytes / 472937 HTML bytes, between 1% and 5%.”
Docs discoverable
Supported
“https://cerebrium.ai/ — Docs link in first-class navigation.”
Machine-readable pricing
Supported
“https://cerebrium.ai/pricing — Parseable GPU/CPU/memory/storage rates and tiers; two plan-label inconsistencies explicitly recorded.”
No anti-bot wall
Supported
“https://cerebrium.ai/ — Public landing/pricing/docs and evidence fetched without challenge.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

9/11

8 full · 1 partial · 82% of applicable checks

Public API
Supported
“https://cerebrium.ai/docs/api-reference/api-keys/create-api-key.md — Documented REST control API and inference endpoints.”
OpenAPI spec
Supported
“https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json — Valid OpenAPI 3.0.0 JSON; 366688 bytes fetched from docs-linked S3 URL.”
MCP server
Supported
“https://cerebrium.ai/docs/mcp — Documented HTTP MCP endpoint; documentation retrieval only, not workload control.”
SDK packages
Not supported
“https://cerebrium.ai/docs/getting-started/introduction.md — Current documented Python package installs CLI; no separate client SDK verified.”
Auth documented
Supported
“https://cerebrium.ai/docs/api-reference/api-keys/create-api-key.md — Bearer service-account token creation, rotation and expiry documented.”
Self-serve credentials
Supported
“https://cerebrium.ai/docs/api-reference/api-keys/create-api-key.md — Programmatic API key creation documented; bootstrapping service account still requires dashboard authentication.”
Webhooks
Supported
“https://cerebrium.ai/docs/endpoints/webhook.md — Documented response forwarding, retries and HMAC signature verification.”
CLI tool
Supported
“https://cerebrium.ai/docs/getting-started/introduction.md — Official pip/brew/Linux/Windows CLI installation.”
Error model
Supported
“https://cerebrium.ai/docs/api-reference/api-keys/create-api-key.md — 400 and 401 JSON schema has message string with documented meanings.”
Rate limits documented
Not supported
“https://cerebrium.ai/docs/llms.txt — Concurrency caps documented, but no request-rate response-header policy found.”
Agent config files
Partially supported
“https://cerebrium.ai/docs/skill.md — One official installable skill surface; no second independent agent configuration surface established.”

06 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 0

The public surface names no coding harness as supported or documented-to-run-here.

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

07 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 4

ISO/IEC 27001
certifiedhosted
“(2026) ISO 27001:2022 Certificate”
Source trust.cerebrium.ai
SOC 2 Type II
certifiedhosted
“Cerebrium has successfully completed its SOC 2 Type 2 audit.”
Source cerebrium.ai
HIPAA
self-attestedhosted
“Cerebrium offers a standardized BAA to all customers who require HIPAA compliance.”
Source cerebrium.ai
GDPR
self-attestedhosted
“Cerebrium supports customer obligations under the General Data Protection Regulation (GDPR).”
Source cerebrium.ai

Regions 4

N. Virginiaus-east-1
Kansas City (Nebius)us-central1
Stockholmeu-north-1
Finland (Nebius)eu-north1

Multi-region beta. Additional regions on request: us-west-2, eu-west-2, eu-central-1, ap-south-1, ap-northeast-1, sa-east-1, ca-central-1, me-central-1. Region-local storage is not synchronized; global apps mount a shared global volume.

Legal

Privacy notice Terms of service

08 Company & presence Facts only, not scored

Company

Headquarters: New York City, USA; founded in Cape Town, South Africa
Founded: 2021
Team size: Not disclosed
Hiring: Jobs board available; openings not exhaustively assessed

Notable people

Michael Louis, CEO & Co-founder

Activity

Last release: — cerebrium.ai
Last blog post: 2026-07-15 — A Low-Latency Architecture for Voice Agents with Real-time Web Search cerebrium.ai

Presence 6

Links found on the public surface scanned; not an exhaustive search.

09 Sources & method How this entry was produced

Public surface only

Everything here was read from cerebrium.ai's unauthenticated pages, docs, pricing and repository on 14 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Inference cloud products →