Limits and quotas

Signal has two kinds of limit. Plan allowances follow your plan and count volume. Rate limits and sizes protect the service and are the same on every plan. This page lists both and what you see when you reach one. Pricing has the counting rules and the worked example.

Plan allowances

	Free	Starter	Growth	Scale	Enterprise
Price per month, billed monthly	$0	$49	$149	$399	From $1,500
Price per month, billed yearly	$0	$39	$119	$319	Custom
Charged once a year	$0	$468	$1,428	$3,828	Custom
Analysed calls a month	200	1,500	5,000	15,000	Custom (50,000+)
Agents	1	3	10	25	Unlimited
Copilot messages a month	20	100	300	600	Custom
Simulated test calls a month	10	50	200	500	Custom
Seats	2	3	10	20	Unlimited, SSO
Price per analysed call at full use, billed monthly	$0	$0.033	$0.030	$0.027	From $0.030

Every plan includes the board, flow, traces, versions, the REST API and the MCP server. Plans differ in volume, not in features. Prices are in US dollars. Analysed calls, copilot messages and simulated test calls are counted per billing period. Agents and seats are totals.

Allowance	What counts	At the limit
Analysed calls	One per 10 minutes started, when Signal takes a call for analysis	Calls keep importing and wait. Analysis resumes after an upgrade or at the reset. No error
Agents	Agents in the workspace now, not a monthly count. The demo agent is excluded	Connecting another is refused with a 402
Copilot messages	Each message in the brief chat or the copilot, and each quick check	The copilot box is disabled and the brief chat refuses. In the app, a notice with an upgrade link
Simulated test calls	One per test and persona in a run. Calibration counts one per test	The whole run is refused before it starts, with a 402
Seats	People in your organization	Set by your plan. Signal does not count or remove members

A Free workspace’s period is the calendar month in UTC. A paid workspace’s period is its billing period. Unused allowance does not carry over. Plan and usage under Settings shows each count against its limit.

Plan limit errors

A request that passes a plan allowance is refused with HTTP 402 and the code quota_exceeded. The API and the MCP server return the same fields as the app, in the API’s error object. error.quota says which limit, how much is used and which plan.

402 from POST /v1/agents/{agentId}/runs

{
  "error": {
    "type": "budget_error",
    "code": "quota_exceeded",
    "message": "This run needs 12 simulated calls and Starter has 4 of 50 left this month. Run fewer tests or upgrade.",
    "param": null,
    "requestId": "req_3f9a1c07d2b84e6a5c1d9b30",
    "quota": {
      "metric": "test_calls",
      "limit": 50,
      "used": 46,
      "plan": "starter",
      "upgradePath": "/billing"
    }
  }
}

An MCP tool returns the same object as a tool error, with the status beside it:

Tool error from start_run

{
  "status": 402,
  "error": {
    "type": "budget_error",
    "code": "quota_exceeded",
    "message": "This run needs 12 simulated calls and Starter has 4 of 50 left this month. Run fewer tests or upgrade.",
    "param": null,
    "requestId": "req_3f9a1c07d2b84e6a5c1d9b30",
    "quota": { "metric": "test_calls", "limit": 50, "used": 46, "plan": "starter", "upgradePath": "/billing" }
  }
}

Field	Meaning
`quota.metric`	The allowance: `analysed_calls`, `agents`, `copilot_messages` or `test_calls`
`quota.limit`	What the plan includes for that metric
`quota.used`	What the workspace has used in the period (agents: the number connected)
`quota.plan`	The plan: `free_org`, `starter`, `growth`, `scale` or `enterprise`
`quota.upgradePath`	The app page to change plan: `/billing`, which is Plan and usage, under the app address

Through the API and the MCP server, only test_calls reaches you today. Starting a run, or calibrating from a signed-in session, spends simulated test calls. The copilot, the brief chat and connecting agents exist in the app only, and calls past the analysed-call allowance wait instead of failing. In the app, the same refusal shows as a notice with See plans. On Enterprise the message ends “Contact us to raise the limit.” Do not retry a 402 quota_exceeded as it is. Nothing changes until the period resets, you upgrade, or you ask for fewer simulated calls. Two other 402 codes are budgets and settings, not the plan:

budget_exceeded: your key’s monthly budget, the agent’s test budget or the workspace’s AI model allowance did not cover the request.
testing_not_configured: testing is not set up for the agent.

The AI model allowance is a workspace limit on Signal’s AI features over the last 30 days. It is separate from your plan, so an upgrade does not raise it. When it is used up, AI features pause, and they resume as older usage leaves the 30-day window. Through the API, a rescore it refuses shows as budget_exceeded.

API rate limits

Rate limits count requests in token buckets. A bucket holds the burst size and refills steadily at the rate, so after a quiet spell you can send a burst, then the sustained rate.

Limit	Applies to	Rate a minute	Burst
All requests	Each API key, or each signed-in person	600	120
Writes (a write route also draws from the all-requests bucket)	Each API key, or each signed-in person	60	20
Workspace	Every key, person and MCP call together, shared with the app	600	600
AI-backed routes (brief chat, test generation, persona drafts, rescore)	The workspace	10	10
MCP endpoint	Each client address	600	120
Failed authentication	Each client address, across the app, the API and MCP	30	30

Every /v1 response carries the tighter of the key’s buckets:

Header	Meaning
`RateLimit-Limit`	The bucket size
`RateLimit-Remaining`	Requests left in the bucket
`RateLimit-Reset`	Seconds until the bucket is full again
`Retry-After`	On a 429 only: seconds to wait before the next request
`Request-Id`	The id of this request, also in `error.requestId`. Quote it when you ask for help

A refused request returns HTTP 429 with the code rate_limited. A client address that has failed authentication too often gets too_many_failed_authentications instead, with or without a valid key, until its failures age out.

429

{
  "error": {
    "type": "rate_limit_error",
    "code": "rate_limited",
    "message": "Too many requests. Retry after 1 second(s).",
    "param": null,
    "requestId": "req_b41e7c90a2d85f3617e0c9a4"
  }
}

Wait for Retry-After, then retry. Treat the numbers as a guide to sustained use, not a guarantee. Calibrating tests needs a signed-in session. Every API key is refused with 403 and the code people_only.

Import limits

These are the limits on the hosted service. They bound how much one import brings in. They are not the plan allowance.

Limit	Value
How far back an import reaches	30 days
Calls in one import	1,000
First import, on approving the brief	The latest 500 calls from the last 30 days

After that, new calls arrive on their own, within minutes of ending, and are not held to the import size. How many are analysed is set by your plan’s analysed-call allowance. A call past it is stored and waits. The import status on Agent config says how many are waiting, such as “120 analysed, 30 waiting for next month or an upgrade.” See Connect Retell.

Copilot limits

Limit	Value
Message length	8,000 characters
Answers at a time	One. Stop ends an answer early

A message counts once against the copilot allowance however many lookups it takes. Each quick check counts as one more. A question that needs too many lookups, a very long call or a very large lookup is cut short, and the copilot answers from what it read. Narrow the question if that happens. The copilot also has a usage limit of its own over the last 30 days, the same on every plan, so an upgrade does not raise it. At that limit it says “This workspace has reached the copilot’s spending limit for this period.” It also pauses when the workspace’s AI model allowance is used up. See Copilot overview.

Version comparisons

A comparison needs enough calls on each version before it gives a verdict. With too few, the measure reads Not enough calls and no verdict is given, however large the difference looks. Wait for more calls on the new version. An issue’s fix verdict also waits until the live version has taken calls for the agent’s grace period, 7 days by default. You can change it with Resolved after on the Issues page. See Versions.

Get started

Core concepts

Guides

AI copilot

Plans and billing

Reference

Limits and quotas

Plan allowances

Plan limit errors

API rate limits

Import limits

Copilot limits

Version comparisons

​Plan allowances

​Plan limit errors

​API rate limits

​Import limits

​Copilot limits

​Version comparisons

Plan allowances

Plan limit errors

API rate limits

Import limits

Copilot limits

Version comparisons