Modal vs Prime Intellect (2026)

Code on Modal reaches other systems through what the customer writes. OIDC tokens authenticate functions to external clouds, cloud buckets mount as filesystems, and secrets hold credentials. Slack notifications report on apps (beta), and examples connect Discord, Google Sheets and Tailscale. Modal has no catalog of connectors, OAuth actions or tool gateway of its own, so the tools are the customer's code.

Sourcemodal.com/llms.txtread 2026-09-22

Agents built in Prime Intellect environments reach outside systems through the tools their harness gives them. Environments declare tools, sandboxes and stateful tool environments. Hosted evaluations can be granted temporary sandbox, instance or tunnel permissions for environments that use tools, and Prime Tunnel exposes local services to them. Prime Intellect names no native connectors, OAuth actions or credential scoping for business systems, so tools are code the customer writes into the environment.

Sourcedocs.primeintellect.ai/hosted-training/what-is-labread 2026-09-22

Retries are first class on Modal. A Retries policy can sit on any function, alongside job queues, fan out with map and spawn, batch and dynamic batching, and gang scheduled clusters. A pipeline that mixes model calls with deterministic steps can be built on these pieces. Sequencing and branching live in the customer's Python. Modal has no multistep workflow primitive that records completed steps and resumes after failure.

Sourcemodal.com/docs/guide/retriesread 2026-09-22

Lab runs agent steps in a loop the customer defines. An environment's harness sets the model's tools, sandboxes, context management and multi turn interaction. For each Hosted Training run, a dedicated Orchestrator manages environment logic, schedules rollout requests and coordinates training. Multi node clusters can be orchestrated with Slurm. The harness and rollout orchestration serve training and evaluation and are written in code. Prime Intellect names no workflow runtime that sequences, branches, retries and routes a deployed agent's production work.

Sourcedocs.primeintellect.ai/hosted-training/what-is-labread 2026-09-22

Scheduled Functions run on a cron expression or a fixed period. Web functions and endpoints boot a container from zero when a request arrives, and job queues hand work to functions as it lands.

Sourcemodal.com/docs/guide/cronread 2026-09-22

Work on Prime Intellect starts when a person or the customer's own code calls it. Hosted evaluations and training runs launch from the dashboard or CLI, and sandboxes and instances start through the API or SDK. Prime Intellect names no schedule, event subscription or other way to start an agent's work without a caller. Cluster alerting notifies people about hardware health, not agents.

Sourcedocs.primeintellect.ai/tutorials-environments/hosted-evaluationsread 2026-09-22

Retrieval systems the customer builds can run on Modal, and its examples embed documents with TEI and run a RAG chatbot over PDFs. Modal does not maintain a retrieval structure over the customer's content that an agent queries. Volumes, Dicts and mounted buckets are storage, and the product itself cannot index, refresh or permission sources.

Sourcemodal.com/llms.txtread 2026-09-22

An environment's dataset is a set of tasks with optional answers for training and scoring. In the search agent guide, the customer builds its own document search inside an environment. Prime Intellect names no retrieval structure it maintains over the customer's content.

Sourcedocs.primeintellect.ai/hosted-training/what-is-labread 2026-09-22

State carries across runs. Sandbox snapshots save and restore a sandbox's filesystem and memory, memory snapshots speed cold starts, volumes persist files, and Dicts and Queues hold data shared across function calls. The agent's code reads that state to carry on. Restored process state belongs to the machine, and the customer can resume or delete it but cannot review or edit it. Modal has no memory layer for agents.

Sourcemodal.com/docs/guide/sandbox-snapshotsread 2026-09-22

What persists on Prime Intellect is compute state. Paused instances keep a workspace directory, and persistent disks hold datasets and checkpoints. Sandbox snapshots that save, restore and fork a sandbox mid run are marked coming soon and have not shipped. Prime Intellect names no memory an agent reads across runs.

Sourcedocs.primeintellect.ai/sandboxes/overviewread 2026-09-22

Work running on Modal has no approval step, consent checkpoint or escalation to a person. Restricted Functions stop untrusted code from touching Modal resources, calling other functions or reaching Modal's APIs. With sandbox networking controls, they give isolation the developer configures, and no person reviews an agent's action.

Sourcemodal.com/docs/guide/restricted-accessread 2026-09-22

Prime Intellect names no approval step, consent checkpoint or escalation to a person for the agents that run in its environments or sandboxes. The developer configures network allow and deny lists per sandbox, which restrict where an agent's code can reach.

Sourcedocs.primeintellect.ai/sandboxes/overviewread 2026-09-22

A SOC 2 Type II audit report is available through Modal's Security Portal at trust.modal.com, and Modal supports HIPAA and has external penetration testing. Identity runs through SSO with Okta, Microsoft Entra or custom SAML, with SCIM provisioning (beta).

Access is managed with role based access control, user groups and service users, and an append only audit log records sensitive actions on Enterprise.

Secrets, Restricted Functions that cannot touch Modal resources, and sandbox networking controls round out the controls, and Sidecars (beta) keep credentials and harness logic in a separate container the agent's code cannot reach.

Sourcemodal.com/docs/guide/securityread 2026-10-23

Sandboxes are microVMs isolated at the hardware level, with network allow and deny lists for egress. Secrets are injected encrypted and never appear in logs or API responses. API keys carry scoped permissions, such as Inference, and team members hold Admin or Member roles. Prime Intellect names no SSO, SCIM or audit log and publishes no SOC 2 or ISO attestation.

Sourcedocs.primeintellect.ai/sandboxes/overviewread 2026-09-22

The workload itself is recorded in detail. Modal keeps real time logs and metrics per function and container, GPU metrics, function stats, and an append only audit log of sensitive workspace actions on Enterprise. Audit logs, function logs and container metrics export to any OpenTelemetry provider or Datadog. Audit stays separate from runtime. Prompts, tool calls, retrieved knowledge and outputs can be inspected step by step only as far as the customer's own code logs them. There is no tracing of each call an agent makes.

Sourcemodal.com/docs/guide/otel-integrationread 2026-09-22

Each run leaves a record. Hosted evaluations store every run with its results in Prime Evals, stream logs to the CLI and dashboard, and can be shared. Hosted Training reports run metrics. Reserved clusters come with Grafana dashboards and alerting on GPU, node and network health. Prime Intellect names no audit log, step by step trace retention or SIEM export.

Sourcedocs.primeintellect.ai/tutorials-environments/hosted-evaluationsread 2026-09-22

Workloads can be pinned to a region. Functions and Sandboxes take a region argument for the container region, dedicated Endpoints set both container and routing regions, and a data residency guide sets out per service what can be pinned and when customer data may leave the region. Region selection carries a price multiplier (1.15x broad, 1.75x narrow). Modal is a managed cloud with no self hosted option, and shared Endpoints do not take a region.

Sourcemodal.com/docs/guide/data-residencyread 2026-09-22

Customers choose where their Prime Intellect compute runs. Before provisioning, GPU availability can be filtered by region (for example United States, Canada or Europe West), by data center and by provider cloud, across more than fifty providers. The training and evaluation stack (prime-rl and verifiers) is open source and runs on the customer's own hardware. Hosted Training and Hosted Evaluations run on infrastructure Prime manages, and no region is published for them.

Sourcedocs.primeintellect.ai/api-reference/check-gpu-availabilityread 2026-09-22

Ready made starting points come as a gallery of runnable examples and a Library of models deployable as Shared or Dedicated Endpoints. The agent examples include Cursor cloud agents, a background coding agent with OpenCode, a coding platform, a Claude Agent SDK Slack bot, a LangGraph agent in a GPU sandbox, a computer use agent over VNC and parallel evals. Developers build from these examples and models, and there is no browsable catalog of agents for a customer to adopt.

Sourcemodal.com/llms.txtread 2026-09-22

The Environments Hub is a community registry of environments, ready to run, for training and evaluation. They span math, coding, games, search and tool use, and multimodal tasks, and the Hub also holds validated benchmark implementations. Lab guides give training recipes for code generation, tool use and search agents. Environments are tasks and scoring for research. The Hub carries no production workflows or agents built for a specific role.

Sourcedocs.primeintellect.ai/tutorials-environments/environmentsread 2026-09-22

Model choice is the customer's throughout. Modal serves models from its Library on Shared Endpoints billed per token or Dedicated Endpoints with the customer's capacity and region. The customer can deploy any open model on GPUs with vLLM or SGLang, as its examples show for DeepSeek, Nemotron and others.

Sourcemodal.com/docs/guide/shared-endpointsread 2026-09-22

The customer chooses the model throughout. Prime Inference is an OpenAI-compatible API that routes requests to a range of model providers. Evaluations run against any model on it or any OpenAI-compatible endpoint the customer brings. Hosted Training lets the customer pick among open weights models (Qwen, Llama, NVIDIA Nemotron, gpt-oss and others), each with its own token price. Trained LoRA adapters deploy behind an OpenAI-compatible endpoint.

Sourcedocs.primeintellect.ai/inference/overviewread 2026-09-22

Official SDKs in Python, JavaScript/TypeScript and Go (the latter two in beta) let outside code call Modal, alongside a full CLI that includes a skills command for coding agents. Web functions and endpoints expose the customer's code as HTTP APIs, and a gRPC API sits behind the open source client.

Sourcemodal.com/llms.txtread 2026-09-22

Outside code reaches Prime Intellect through a REST API (instances, availability, disks, clusters, sandboxes and chat completions) with scoped API keys, the prime CLI and a Python SDK for sandbox lifecycles. With the open source verifiers and prime-rl libraries, customers build and publish their own environments to the Environments Hub. The API, CLI and SDK are stable. Prime Intellect publishes no MCP server.

Sourcedocs.primeintellect.ai/llms.txtread 2026-09-22

Evaluations run on Modal, but scoring them is left to other tools. Its example runs massively parallel evals with Harbor in Modal Sandboxes, and its reinforcement learning examples use verl and TRL, with the datasets, graders and scoring belonging to those frameworks. Modal has no fixtures, scoring, quality gates or comparison of agent runs of its own.

Sourcemodal.com/llms.txtread 2026-09-22

Evaluating the customer's agent is a core product. An environment packages a dataset of tasks, the harness the model runs in (tools, sandboxes, multi turn interaction) and a rubric of reward functions and metrics that scores it.

Hosted Evaluations run that environment against Prime Inference or any OpenAI-compatible endpoint, from the dashboard or CLI, and store each run with its logs and results in Prime Evals. The Environments Hub adds validated benchmarks such as AIME, MATH-500 and Humanity's Last Exam. Teams can test an agent on these datasets before production and score it the same way on every run.

Sourcedocs.primeintellect.ai/tutorials-environments/hosted-evaluationsread 2026-09-22

Computer use agents can run on Modal's machines. VM Sandboxes, now generally available, give an agent a full Linux computer that can run Docker stacks, graphical environments and mobile simulators. In one example, a Browser Use agent drives Chromium inside a Modal Sandbox, watched over VNC, with the model served from a Modal Endpoint. Control of the browser comes from Browser Use, a separate library. Modal has no API for screenshots, clicks or typing, so it supplies the environment but not the control.

Sourcemodal.com/blog/vm-sandboxes-agent-computersread 2026-10-23

Browser use exists only inside training environments. The verifiers library's BrowserEnv lets an agent navigate and act on web pages, either in a DOM mode through Stagehand or in a computer use mode based on vision. The browser itself runs on Browserbase, a separate service with its own account and billing, sold beside the platform and not part of it. Prime Sandboxes are VMs for running code. Prime Intellect hosts no browser or desktop of its own for an agent to operate on web interfaces or desktop environments.

Sourcedocs.primeintellect.ai/guides/browser-environmentsread 2026-09-22