Serverless compute: read the guide
Scanned 6 Oct 2026 · Schema v5 · features v20
- From
- $250/mo
usage (per-second CPU/mem/GPU) + plan tier (seats + monthly credits + features); Sandbox/Notebook compute billed at 3x standard
- Free tier
- Not documented
$30/mo free compute credits on Starter (+ 1 TiB/mo egress + 1 TiB-mo storage free); startup + academic credit grants (up to $10k)
- Isolation
- Kata / gVisor
hardened or user-space kernel
- Regions
- 9
United States (broad; 1.15x) — narrow: us-east (Virginia, default routing), us-central, us-south, us-west (1.75x) · European Economic Area (broad) — narrow: eu-west, eu-north, eu-south · Asia-Pacific (broad) — narrow: ap-northeast, ap-southeast, ap-south, ap-melbourne; jp (Japan), au (Australia) · United Kingdom · Canada · Middle East +3
- Capabilities
- 24 / 57
7 partial · 19 fail · 4 not assessed
- Agent readiness
- 11/11 · 9/11
read · drive, pre-login surface
Advertised for
AI agent sandboxes · LLM inference · Model inference endpoints · Training finetuning · Batch · Notebooks · Code execution · Web servers
Built for
Developers, then technical
- · Python-first 'code as config' — decorators, no YAML/Dockerfile; CLI + SDK driven (modal run/deploy/shell/skills)
- · Systems/GPU vocabulary (gVisor vs VM runtime, memory snapshots, SNI proxy, B300/H200, i6pn, RDMA)
- · Per-second compute units + per-token endpoints; $30/mo free credits to capture individual developers
01 Pricing usage (per-second CPU/mem/GPU) + plan tier (seats + monthly credits + features); Sandbox/Notebook compute billed at 3x standard
| Tier | EntryStarter | Team | TopEnterprise |
|---|---|---|---|
| Price | $0/mo + compute; $30/mo free credits | $250/mo + compute; $100/mo free credits | Custom |
| Includes | $30/mo compute credits · 3 workspace seats · 100 containers + 10 GPU concurrency · 200 deployed apps · 5 deployed crons · 1-day log retention · region selection · 1 TiB/mo free network egress · SOC 2 | $100/mo compute credits · unlimited seats · 5000 containers + 50 GPU concurrency · 1000 deployed apps · unlimited crons · 30-day logs · custom domains · Static IP proxy · RBAC · 3-version deployment rollbacks · environment-level budgets · 10 TiB/mo free egress | Volume-based discounts · unlimited seats · higher GPU concurrency · audit logs · Okta/SAML SSO · HIPAA BAA · private-Slack support · embedded ML engineering · AWS/GCP marketplace committed spend · 100 TiB/mo free egress |
| Seats | 3 | — | — |
| Transfer | 1024 GB | 10240 GB | 102400 GB |
| Storage | 1024 GB | 1024 GB | — |
| Transfer overage | $0.04/GB | $0.04/GB | — |
| Storage overage | $0.09/GB | $0.09/GB | — |
| Compute hours overage | $0.04716/h | $0.04716/h | — |
Free tier: $30/mo free compute credits on Starter (+ 1 TiB/mo egress + 1 TiB-mo storage free); startup + academic credit grants (up to $10k)
per-second (CPU core-sec, GiB-sec, GPU-sec) + per-GiB-month storage·Card required: unconfirmed·modal.com
Overages: GPU per-second: T4 $0.000164, L4 $0.000222, A10 $0.000306, L40S $0.000542, A100-40 $0.000583, A100-80 $0.000694, RTX PRO 6000 $0.000842, H100 $0.001097, H200 $0.001261, B200 $0.001736, B300 $0.001972. CPU $0.0000131/core/s (~$0.0472/core-hr, min 0.125 core), memory $0.00000222/GiB/s. Sandbox + Notebook compute = 3x (CPU $0.00003942/core/s, mem $0.00000667/GiB/s; GPU at standard). Volumes $0.09/GiB-mo (1 TiB/mo free). Network egress $0.04/GiB beyond the plan allotment. Region selection 1.15x (broad) / 1.75x (narrow); non-preemptible 3x. Shared Endpoints billed per token at rates shown in the dashboard; plan credits do NOT cover them.
02 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
ephemeral containers + persistent Volumes (v1/v2) / cloud bucket mounts; Sandbox filesystem, directory AND memory snapshots (restorable, TTL'd)
Snapshots / forks
Yes
Resources & limits
Storage
Volumes (distributed FS) + cloud bucket mounts (BYO); $0.09/GiB-mo (1 TiB/mo free); ephemeral container FS otherwise
Limits & quotas
Starter: 100 containers + 10 GPU concurrency, 3 seats, 200 deployed apps, 5 crons, 1-day logs; Team: 5000 containers + 50 GPU concurrency, unlimited seats, 1000 apps, 30-day logs, 3 rollback versions; Enterprise custom. Workspace rate limit 200 Function calls/HTTP req per s (5s burst) -> 429; web request bodies <= 4 GiB; Shared Endpoints have per-model concurrency caps (429). Memory snapshots expire after 7 days.
GPU
Yes
Access
Deploy interface
clisdk
SDK languages
PythonJavaScriptGo
Network & secrets
Egress controls
Yes
Secrets
Yes
Bring your own cloud
No
Placement & use
Jurisdiction
region selection across 20+ selectors — broad us / eu / ap (1.15x) and narrow us-east/central/south/west, eu-west/north/south, ap-northeast/southeast/south/melbourne, jp, au, uk, ca, me, sa, af, mx (1.75x); default input routing via us-east (Virginia, USA); Shared Endpoints route via us-west
Advertised workloads
AI agent sandboxesLLM inferenceModel inference endpointsTraining finetuningBatchNotebooksCode executionWeb servers
03 Capabilities 24 pass · 7 partial · 19 fail · 57 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 7/9
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).
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.
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.
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 applicable
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 assessed
Networking & delivery 5/8
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).
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 applicable
Developer access 4/9
Public APIDocumented programmatic API.
Supported
OpenAPI specMachine-readable OpenAPI / Swagger spec published.
Not supported
CLIOfficial command-line tool.
Supported
SDKOfficial client library/libraries.
Supported
SSH accessDirect SSH into workloads.
Partially supported
Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.
Supported
Git deployDeploy from a Git repo / push-to-deploy.
Not 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 applicable
AI & agents 4/10
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.
Not 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).
Supported
LLM gatewayRoutes LLM API calls through the platform (multi-provider).
Not supported
BYOK for LLMsBring-your-own LLM provider keys.
Not applicable
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).
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 assessed
Data 0/1
First-party databasePlatform-provided managed database.
Partially 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 applicable
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 applicable
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 applicable
Platform & operations 2/6
Scheduled tasksCron / scheduled job primitive.
Supported
Durable workflowsDurable execution / long-running workflow primitive.
Partially 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 2/7
Built-in authPlatform-provided authentication / IAM for workloads.
Partially supported
SSO / SAMLEnterprise single sign-on.
Partially supported
Secrets managementFirst-class secrets storage / injection.
Supported
TeamsMulti-user team accounts.
Supported
SharingShare a running workload/resource via link (optionally gated).
Partially 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 assessed
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 assessed
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.
- Collaborative GPU notebooks (real-time multi-user)notebooks
“Notebooks — GPU-backed collaborative notebooks ('Launch GPU-backed Notebooks in seconds'); real-time multi-user editing; billed at Sandbox (3x) compute rates.” modal.com
- Distributed Dicts + Queues (cross-container data structures)distributed-primitives
“Distributed Queues/Dicts for cross-container coordination and data passing.” modal.com
- Multi-node clusters (RDMA/InfiniBand, i6pn) for distributed trainingmulti-node-cluster
“Multi-node clusters with i6pn private networking + RDMA/InfiniBand for distributed training/inference.” modal.com
- Sandbox Sidecars (Beta) — auxiliary containers attached to a Sandboxsandbox-sidecars
“[Sidecars let you run additional] containers over TCP/UDP, making them ideal for: Separating an agent harness from its execution environment, by running the agent in one container and its tool calls in another ... Credentials injection, by running a proxy in a separate, trusted container ... Splitting out complex multi-service applications over separate containers, such as databases, caches or worker processes, similar to Docker Compose.” modal.com
04 Agent readiness Pre-login surface · counts, not a grade
Can an agent read it?
parse-ability · docs, metadata, machine-readable surfaces
11/11
7 full · 4 partial · 100% of applicable checks
- llms.txtSupported
- llms-full.txtSupported
- robots.txt AI policyPartially supported
- JSON-LDPartially supported
- SitemapSupported
- Meta tagsSupported
- Markdown negotiationPartially supported
- Content efficiencyPartially supported
- Docs discoverableSupported
- Machine-readable pricingSupported
- No anti-bot wallSupported
Can an agent drive it?
act-ability · APIs, SDKs, MCP, credentials, webhooks
9/11
5 full · 4 partial · 82% of applicable checks
- Public APISupported
- OpenAPI specNot supported
- MCP serverNot supported
- SDK packagesSupported
- Auth documentedSupported
- Self-serve credentialsPartially supported
- WebhooksPartially supported
- CLI toolSupported
- Error modelPartially supported
- Rate limits documentedPartially supported
- Agent config filesSupported
05 Coding harnesses Which agents and IDEs are documented to run here
Advertised integrations 3
- Claude Code AnthropicSupported
- Codex CLI OpenAISupported
- OpenCode opencodeSupported
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.
06 Compliance & regions Standards held, with ordinal rigor; never a score
Certifications held 2
- SOC 2 Type IIcertifiedhostedSOC 2 Type 2 — stated on the docs security page; pricing table lists 'SOC 2 compliance: Included' on every plan. Report gated behind the trust portal (JS-rendered; not probed).
- HIPAAenterprise-onlyhostedBAA on Enterprise only; Volumes v2 are in scope, Volumes v1 / Images / Memory Snapshots are explicitly OUT of BAA scope — load-bearing for PHI workloads.
Regions 9
- United States (broad; 1.15x) — narrow: us-east (Virginia, default routing), us-central, us-south, us-west (1.75x)us
- European Economic Area (broad) — narrow: eu-west, eu-north, eu-southeu
- Asia-Pacific (broad) — narrow: ap-northeast, ap-southeast, ap-south, ap-melbourne; jp (Japan), au (Australia)ap
- United Kingdomuk
- Canadaca
- Middle Eastme
- South Americasa
- Africaaf
- Mexicomx
Region SELECTORS, not a datacenter list: Modal schedules onto a multi-cloud capacity pool and `region=` constrains placement at a 1.15x (broad) / 1.75x (narrow) multiplier; 'more granular region definitions' via sales. Default: inputs routed via us-east (Virginia). Shared inference Endpoints route via us-west. Previous scan listed 6 representative regions incl. an OCI us-ashburn-1 — the live page now exposes the full selector table.
07 Company & presence Facts only, not scored
Company
- Headquarters
- New York City, USA
- Founded
- 2021
- Team size
- not disclosed (38 open roles across 4 offices, 2026-10)
Funding
- as of 2026-10total disclosed · $466M+modal.com
Notable people
- Erik Bernhardsson (CEO — ex-Spotify; created Luigi, Annoy)
- Akshat Bubna (co-founder)
Activity
Presence 8
Links found on the public surface scanned; not an exhaustive search.
08 Sources & method How this entry was produced
Public surface only
Everything here was read from modal.com's unauthenticated pages, docs, pricing and repository on 6 Oct 2026. Nothing behind a login was used.
Statuses, not scores
Capabilities are pass, partial or fail against a written rubric (features v20). “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
- v20
- Keys tracked today
- 61
- Assessed on this entry
- 57
Something wrong on this page?
