> ## Documentation Index
> Fetch the complete documentation index at: https://docs.voyager.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Fix generation and credit problems

> Use the message shown by Voyager to resolve credit limits, provider failures, and waiting generations.

Open the chat's **Jobs** panel and read the status before trying a generation again. In notifications, the provider name tells you which account needs attention. Model names, plan names, and counts can vary in the messages below.

<Warning>
  A new attempt can create a new charge. If a notification says **Continued on** another provider (for example **Higgsfield is out of credits**, **Continued on Voyager credits**), check that generation first. Automatic fallback may already have kept the work going on a different account.
</Warning>

## Out of Voyager credits

The workspace cannot pay for this generation with its available Voyager credits. The chat may also say **Your workspace is out of Voyager credits.**, followed by the amount needed and a billing link.

1. Open [Voyager billing](https://voyager.so/dashboard/billing) and check the selected workspace and balance.
2. Buy a credit pack, enable or fix auto-reload, wait for credits to reset, or connect your own media key.
3. Check whether fallback already continued the original job. If it stopped, ask the agent to continue only the unfinished work after credits or another connection are available.

**Check:** The existing job is progressing, or the stopped work can start after the balance or connection is fixed. Earlier completed results remain usable.

**Still stuck:** Use [Get help…](/help/get-help) from the chat and include the job ID, workspace, and credit message.

## “Higgsfield is out of credits”, “Continued on Voyager credits”

A provider in your list ran out of credits, and automatic fallback moved the generation to the next one. The title names the provider that ran out, such as **FAL is out of credits**. The line below starts **Continued on** and names where the work went. For a batch it reads, for example, **3 generations continued on Voyager credits**.

1. Don't submit the work again: it is already running on the next provider. Check it in the chat's **Jobs** panel.
2. Choose **Open Settings** to top up the provider that ran out, or change the order under **Settings → Accounts → Generation providers**.
3. If you don't want work to move to another account, turn off **Automatic fallback**. See [Generation providers](/account/generation-providers#understand-automatic-fallback).

**Check:** The job finishes, and the next generation uses the provider you intended.

**Still stuck:** Include the job ID and the full notification in **Get help…**.

## Automatic fallback is off, so nothing was generated

The chosen provider ran out of credits, and Voyager stopped rather than using another account.

1. Read the notification title to identify the provider. It may say **Out of Voyager credits** or, for example, **FAL is out of credits**.
2. Choose **Open Settings** and check that provider under **Settings → Accounts → Generation providers**.
3. Add funds to that account, or deliberately change which provider should pay before trying the stopped work again.

<Warning>
  Turning **Automatic fallback** on allows Voyager to try other providers in your list, including accounts with separate bills. See [Generation providers](/account/generation-providers).
</Warning>

**Check:** The next attempt uses the provider you intended. For a batch, the notification may instead say how many generations did not run.

**Still stuck:** Include the notification and provider name in a support request.

## Higgsfield plan credits ran out

Voyager used up the available Higgsfield plan credits and continued on another connection.

1. Read the rest of the notification. It names where the generation continued, such as **on your Higgsfield API balance**.
2. Inspect the existing job; do not submit another copy if it is progressing.
3. Before the next generation, review the [Higgsfield plan and API balance distinction](/account/generation-providers#higgsfield-plan-versus-api-balance) and change fallback or your saved connections if needed.

**Check:** The current result finishes, and the next job uses the account you chose.

**Still stuck:** Include the job ID and the full fallback notification in **Get help…**.

## Voyager sign-in expired

Voyager can no longer use the saved account sign-in. A Higgsfield connection can show **Higgsfield sign-in expired** instead.

1. Choose **Reconnect** in the notification, or open the affected account in **Settings → Accounts**.
2. Finish signing in through the browser and choose the intended workspace if asked.
3. Check the existing job: it may already have continued on another provider.

**Check:** The account is connected again, and new work can use it.

**Still stuck:** Follow [Setup problems](/help/setup-problems), then send the sign-in error and affected job through **Get help…**.

## FAL rejected your key

The provider did not accept its saved API key. The same notification can name Google, ElevenLabs, or another key-based connection.

1. Choose **Update key**, or open that provider in **Settings → Accounts**.
2. Check the key in your provider account and replace it in Voyager if it has expired, been revoked, or belongs to the wrong account.
3. Save it and check the connection status. Review any **Continued** notification before retrying the generation.

**Check:** The row no longer shows **Rejected**, and a new job can use the intended account.

**Still stuck:** Tell support the provider and exact error. Never send the API key.

## FAL is unavailable

The provider could not handle the request. The notification may name another provider or say it **is busy**.

1. Read whether Voyager continued on another provider.
2. If it did, watch the existing job in **Jobs**.
3. If it stopped, wait before retrying or choose another provider after reviewing its billing.

**Check:** The original job completes, or a later attempt progresses after the provider recovers.

**Still stuck:** Send the model, provider, job ID, and time of the failure through **Get help…**.

## Waiting for a free slot…

Your plan's available parallel generations are already running. The message can include how many are running and your plan name.

1. Leave the waiting job in place; it starts automatically when a slot opens.
2. Check **Jobs** to see which generations are running.
3. If Voyager eventually stops waiting, let a running generation finish before asking it to start the stopped work again.

That wait is not a second generation, and the refused attempt has not been charged. Plans allow different amounts of parallel work; see [pricing](https://voyager.so/pricing).

**Check:** The status changes from waiting to running when a slot is available.

**Still stuck:** Include the waiting message, job ID, and the other jobs' statuses in **Get help…**.

## Waiting for auto-reload to top up credits…

Auto-reload is buying credits so this job can start.

1. Let the existing job wait; do not start a replacement.
2. Check **Auto-reload** in [billing](https://voyager.so/dashboard/billing) if the wait continues.
3. If the job stops with **Auto-reload did not top up the workspace's Voyager credits in time.**, fix the purchase or buy a credit pack, then ask the agent to restart the stopped work.

**Check:** The balance increases and the waiting job starts, or the replacement starts after the original has stopped. A request refused while waiting for the top-up was not charged.

**Still stuck:** Send the job ID and the auto-reload status to support. Do not send payment card details.

## This workspace has reached its daily limit on generated media.

The workspace hit a daily media limit, which is different from having no credits.

1. Read the remedy shown with the message.
2. Open [billing](https://voyager.so/dashboard/billing) to review the workspace's plan, or wait for the daily limit to clear.
3. Retry only the stopped work afterward. Do not keep buying credit packs to fix a limit that is not the balance.

**Check:** A new request is accepted after the limit clears or the applicable plan change takes effect.

**Still stuck:** Include the full message and workspace in **Get help…**.

## Seedance 2.5 needs Voyager Creator or higher.

The requested model is not included in the current Voyager plan. Other model refusals name the model and plan they require.

1. Ask the agent to choose an included model, or review the options on [pricing](https://voyager.so/pricing).
2. If you choose to upgrade, make the change in [billing](https://voyager.so/dashboard/billing).
3. Continue with the included model or after the plan change is available.

This message is not an out-of-credits error. Adding credits alone does not unlock the model, and Voyager does not automatically switch to your own keys for this refusal.

**Check:** The selected model is included on the plan and the generation can begin.

**Still stuck:** Send the model name, plan shown in Voyager, and refusal through **Get help…**.

## Ask a workspace admin to give you a Voyager seat.

Your account does not have a seat on the workspace's Voyager plan.

1. Ask a workspace admin to open [billing](https://voyager.so/dashboard/billing) and assign a seat.
2. Return to **Settings → Accounts** and choose **Check connection**.
3. Alternatively, select your own Claude or ChatGPT subscription for chat and your own media keys for generation.

**Check:** The seat refusal clears for the intended workspace.

**Still stuck:** Include the workspace name and refusal in a private support request.

## Video generation needs a paid plan.

This generation was set to use Voyager credits, but the workspace has no paid plan. Image or audio requests name that kind of generation instead.

1. If you want Voyager to handle generation billing, review [pricing](https://voyager.so/pricing) and choose a plan in [billing](https://voyager.so/dashboard/billing).
2. If you want to use your own account, connect and enable the appropriate [generation provider](/account/generation-providers), then ask the agent to use it.

A paid Voyager plan is optional when you use your own media keys. **Models through Voyager need a Voyager plan.** is the equivalent chat message; select your own Claude or ChatGPT subscription to continue without a Voyager plan.

**Check:** The generation uses your chosen provider, or the newly available Voyager plan.

**Still stuck:** Send support the full refusal and the provider you expected to use.

## Your workspace is out of Voyager plan credits for chat.

Chat through Voyager has used up the available credit pool.

1. Buy a credit pack or enable or fix auto-reload in [billing](https://voyager.so/dashboard/billing), or wait for the next credit reset.
2. To continue with your own subscription, select your Claude or ChatGPT account in the model picker.

**Check:** The next request completes on the selected account. Switching providers can continue in a new chat.

**Still stuck:** Send the credit message and selected account through **Get help…**.

## An admin turned off chat through Voyager for this workspace.

The workspace's chat setting prevents use of Voyager models.

1. Ask an admin to turn chat back on in [billing](https://voyager.so/dashboard/billing), or select your own Claude or ChatGPT subscription.
2. If the message instead says **Chat through Voyager reached the chat limit an admin set for this workspace this month.**, ask an admin to review that limit. The message may include the workspace's specific limit.

**Check:** Chat responds after the setting changes or you choose another account. Buying credits alone does not change an admin's chat setting or limit.

**Still stuck:** Send the full message and workspace name through **Get help…**.

## Payment failed.

The last Voyager payment failed, which pauses chat through Voyager.

1. Open [billing](https://voyager.so/dashboard/billing) and follow its payment instructions.
2. Update or confirm the payment as requested.
3. Retry the chat, or choose your own Claude or ChatGPT subscription to continue.

Generating media with available plan credits can still work while this chat restriction is in place.

**Check:** The payment warning clears and chat through Voyager responds again.

**Still stuck:** Send the warning to support privately, without card details.

## The media provider rejected this request (provider\_rejected)

The provider refused the inputs. The rest of the message may name an input or say that Voyager could not read a reason.

1. Read the full error and keep any **Voyager request ID** it includes.
2. Ask the agent to check the named input against the selected model's requirements, such as supported image size, video duration, or file format.
3. Make a changed attempt only when there is a specific input to fix. If the reason is unclear, stop and ask support rather than resubmitting unchanged inputs.

Voyager does not use automatic fallback to fix rejected inputs.

**Check:** The revised request is accepted and begins generating.

**Still stuck:** Use **Get help…** and include the complete error, model, and Voyager request ID.

## The app stopped while submitting this generation.

The provider may have accepted the generation before Voyager could confirm it.

1. Reopen the affected chat and inspect the original job in **Jobs**.
2. Check that provider account's generation history when available.
3. Ask the agent to inspect or collect the existing job before starting another paid generation.

**Check:** You have a confirmed result or confirmed failure for the original job before making another attempt.

**Still stuck:** Send the original job ID, approximate submission time, provider, and error through **Get help…**.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.