Modal
$30 in credits refresh on a published schedule.
https://{workspace}--{endpoint}.{region}.modal.direct/v1Models mentioned
moonshotai/Kimi-K3Equivalent paid value
How this was valued: Face value of the Starter plan's recurring compute credit. Any one deployed model can consume the shared balance; model rows are not additive.
Limits and terms
- Plan
- Starter
- Plan Price USD Per Month
- 0
- Included Credit USD Per Month
- 30
- Containers
- 100
- GPU Concurrency
- 10
- Shared Endpoint Credit Restriction
- Since 2026-09-01, plan-included credits cannot pay Shared Endpoint usage; they remain usable for user-deployed and dedicated endpoints.
What happens to your prompts?
Modal does not store ordinary endpoint payloads or train on Customer Data without written consent.
- Plan Scope
- Modal serverless compute and Modal-hosted inference endpoints; Functions, endpoints, logs, volumes, and snapshots have different retention.
- Prompt Retention
- Server and inference endpoint request payloads are not stored and are proxied to the customer's container. Function arguments and return values can be retained encrypted for up to seven days.
- Response Retention
- Endpoint responses are not stored; Function return values can remain up to seven days. Customer-created volumes and images persist until deleted.
- Ordinary Logging
- App and container logs persist one day on Starter, 30 days on Team, and per contract on Enterprise; account and resource metadata persists for the account lifetime.
- Model Training
- Modal contractually says it will not train an AI model on Customer Data or export it into an LLM without prior written customer consent.
- Product Improvement
- Modal collects aggregate de-identified operational data, but Customer Data is licensed only as necessary to provide the service and is excluded from model training without consent.
- Human Or Operator Access
- Modal says it will not access code, function inputs or outputs, or stored customer data. Logs and metadata are accessed only with customer permission for troubleshooting, subject to service/security exceptions in the terms.
- Subprocessors And Routing
- Modal pools compute across cloud providers and lists AI-tool subprocessors under its DPA; customers can select processing regions.
- Deletion Controls
- Inference endpoint payloads are never written to disk; function data expires within seven days; volumes and images persist until customer deletion; portability and erasure requests are supported.
- Caveat
- Modal is infrastructure, so code deployed by the customer can itself save or forward prompts. The endpoint ZDR statement covers Modal's proxy, not application-level logging inside the container.
Governing documents
- Terms Of Service
- https://modal.com/legal/terms
- Privacy Policy
- https://modal.com/legal/privacy-policy
Eligibility
- Account Required
- Yes
- Payment Method Required
- Yes
Primary sources
Before you build with Modal
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every region.
Resolve the live model route
This snapshot records 1 model ID. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. The recorded base endpoint is https://{workspace}--{endpoint}.{region}.modal.direct/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. A payment method is required. A zero-cost allowance can still be useful, but protect the account with provider-side budgets or alerts before sending production traffic. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “Private”: Modal does not store ordinary endpoint payloads or train on Customer Data without written consent. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 8 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.