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

# Frequently Asked Questions

> Answers to common questions about the Perplexity API, covering models, output and capabilities, search behavior, billing and limits, errors, data privacy, and support.

## Models

> [accordion] Does the API Currently Support Web Browsing?
>
> Yes. The Agent API provides a built-in [web search tool](https://docs.perplexity.ai/docs/agent-api/tools/web-search.md), and research-backed [effort levels](https://docs.perplexity.ai/docs/agent-api/effort.md) include search by default.

> [accordion] What Are the Context Windows for Each Model?
>
> Context window size varies by model. See the [Agent API models page](https://docs.perplexity.ai/docs/agent-api/models.md) and the linked provider documentation.

> [accordion] Do You Support Fine-Tuning?
>
> Currently, we do not support fine-tuning.

> [accordion] How Are Models Versioned and Deprecated?
>
> When a model is retired, we announce it in the [changelog](https://docs.perplexity.ai/docs/resources/changelog.md) along with a recommended replacement. To avoid unexpected model changes, pin an explicit model ID in your requests rather than relying on a default. Pinning doesn't prevent retirement, so watch the changelog for deprecation notices. The current list of available models is on the [Agent API models](https://docs.perplexity.ai/docs/agent-api/models.md) page.

## Output & Capabilities

> [accordion] Can I Get Structured (JSON) Output?
>
> Yes. Use the `text.format` field to constrain a response to a JSON schema. See [Structured Outputs](https://docs.perplexity.ai/docs/agent-api/output-control.md#structured-outputs) for examples.

> [accordion] Does the API Support Streaming Responses?
>
> Yes. Pass `stream: true` to receive the response incrementally as it is generated, instead of waiting for the full result. See [Streaming Responses](https://docs.perplexity.ai/docs/agent-api/output-control.md#streaming-responses). The [official SDKs](https://docs.perplexity.ai/docs/sdk/overview.md) expose streaming directly.

> [accordion] Does the API Support Tool or Function Calling?
>
> Yes. The Agent API provides built-in tools, including [web search](https://docs.perplexity.ai/docs/agent-api/tools/web-search.md), [image search](https://docs.perplexity.ai/docs/agent-api/tools/image-search.md), [fetch URL content](https://docs.perplexity.ai/docs/agent-api/tools/fetch-url-content.md), [people search](https://docs.perplexity.ai/docs/agent-api/tools/people-search.md), [finance search](https://docs.perplexity.ai/docs/agent-api/tools/finance-search.md), and a [code sandbox](https://docs.perplexity.ai/docs/agent-api/tools/sandbox.md). The model decides when to call them while answering your request. To call your own code, declare [custom functions](https://docs.perplexity.ai/docs/agent-api/tools/custom-functions.md): the model requests a call, and your application runs it and returns the result. You can also connect [MCP servers](https://docs.perplexity.ai/docs/agent-api/tools/mcp.md) and [connectors](https://docs.perplexity.ai/docs/agent-api/tools/connectors.md). See the [tools overview](https://docs.perplexity.ai/docs/agent-api/tools/overview.md).

> [accordion] To What Extent Is the API OpenAI Compatible?
>
> It depends on the API.
>
> * **Orchestrator API (private preview):** accepts the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages formats at `https://api.perplexity.ai/orchestrator/v1`. See the [Orchestrator API quickstart](https://docs.perplexity.ai/docs/orchestrator/quickstart.md).
> * **Agent API:** supports the OpenAI Responses API interface. Point an OpenAI client at `https://api.perplexity.ai/v1` with your Perplexity API key and call `client.responses.create()`. `POST /v1/responses` is accepted as an alias for the canonical `POST /v1/agent`. Some defaults and Perplexity extensions differ from OpenAI's. See [OpenAI Compatibility](https://docs.perplexity.ai/docs/agent-api/openai-compatibility.md) for the differences.

> [accordion] Are the Reasoning Tokens in Deep Research the Same as the CoTs in the Answer?
>
> No. In [Sonar Deep Research](https://docs.perplexity.ai/docs/legacy/sonar/models/sonar-deep-research), reasoning tokens are what the model uses to reason through the research material before it writes the final output. They're reported separately from completion tokens in `usage.reasoning_tokens` and billed at their own rate.

## Search & Results

> [accordion] Why Are the Results from the API Different from the UI?
>
> 1. The API uses the same search system as the UI with differences in configuration, so their outputs may differ.
> 2. The underlying AI model might differ between the API and the UI for a given query.

> [accordion] Is the Internet Data Access Provided by the API Identical to That of Perplexity's Web Interface?
>
> Not exactly. The API and the web interface share search infrastructure, but their tools, configuration, and models differ, so results can differ.

> [accordion] Does the API Use Content Filtering or SafeSearch?
>
> It depends on the tool. In the Agent API, the [image search tool](https://docs.perplexity.ai/docs/agent-api/tools/image-search.md) applies SafeSearch by default: `filters.safe_search` defaults to `true`. The `web_search` tool has no SafeSearch setting. Legacy Sonar models apply SafeSearch to web results by default.

## Account, Billing & Limits

> [accordion] How Does API Pricing Work?
>
> Pricing is usage-based and varies by API:
>
> * **Orchestrator API:** per token at each model's published rates, with no per-request fees.
> * **Agent API:** per token at each model's published rates, plus tool fees. Most tools bill per call. `sandbox` bills per session (a 20-minute billing window), and tools called from inside the sandbox bill at their standard rates.
> * **Search API:** per successful request.
> * **Embeddings API:** per token.
> * **Decisions API:** per input token. Output tokens are free.
>
> See the full breakdown on the [Pricing page](https://docs.perplexity.ai/docs/getting-started/pricing.md).

> [accordion] How Do I Add Credits or Set Up Billing?
>
> Purchase API credits in the [Billing page](https://console.perplexity.ai/project/billing) in the API Console. Enable **auto top-up** to add credits automatically when your balance runs low and avoid interrupted service. You can also buy credits through the [AWS Marketplace](https://docs.perplexity.ai/docs/resources/aws-marketplace.md) for consolidated billing, or [contact our sales team](https://perplexity.typeform.com/to/m3WnMaG6) for enterprise procurement. Your [usage tier](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md) advances automatically as your cumulative purchases grow.

> [accordion] How Can I Upgrade to the Next Usage Tier?
>
> Your usage tier advances automatically when your all-time credit purchases reach the next threshold. If you need higher limits than your tier allows, [request a custom limit](https://perplexity.typeform.com/to/yctmfyVT).
>
> | Tier | Credit Purchase (all time) |
> | - | - |
> | Tier 0 | \$0 |
> | Tier 1 | \$50 |
> | Tier 2 | \$250 |
> | Tier 3 | \$500 |
> | Tier 4 | \$1000 |
> | Tier 5 | \$5000 |
>
> See [Rate Limits & Usage Tiers](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md) for the limits at each tier.

> [accordion] What Are the Limitations to the Number of API Calls?
>
> Limits depend on the API and your usage tier. The Agent API applies both a request limit and per-model token limits. See [Rate Limits & Usage Tiers](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md).

> [accordion] How Can I Track My Spend/Usage per API Key?
>
> If you're an Admin, open the [Billing page](https://console.perplexity.ai/project/billing) in the API Console. If your organization has more than one API key, use the API key filter in usage analytics to see cost and usage for the keys you select. Some invoice line items under **Invoice history** also end with the last 4 characters of the API key, for example `pro (743S)`, but not every invoice includes this breakdown.

## Errors & Troubleshooting

> [accordion] How Should I Respond to 401: Authorization Errors?
>
> A 401 means the request couldn't be authenticated. Check that you're sending a current API key in the `Authorization: Bearer` header and that the key hasn't been deleted. If your account runs out of credits, requests can return `402 Payment Required` instead. Add credits on the [Billing page](https://console.perplexity.ai/project/billing), and turn on auto top-up to avoid interruptions.

> [accordion] How Should I Handle 429: Too Many Requests Errors?
>
> A 429 means you've exceeded a rate limit. Limits and limiter behavior vary by API, and the Agent API applies both a request limit and per-model token limits. See [Rate Limits & Usage Tiers](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md). On a 429, wait at least the `Retry-After` interval, then retry with exponential backoff and jitter. The SDK examples in [Error Handling](https://docs.perplexity.ai/docs/sdk/error-handling.md) show the backoff shape; for Agent API token limits, start the delay from `Retry-After`, not from a fixed base. For sustained higher throughput, upgrade your tier or [request a custom limit](https://perplexity.typeform.com/to/yctmfyVT).

> [accordion] What Should I Do About 5xx or Connection and Timeout Errors?
>
> 5xx responses indicate a transient server-side issue, and connection or timeout errors usually point to a network problem. Retry these with exponential backoff, set sensible client timeouts, and log the `X-Request-ID` response header to include when you contact support. The [Error Handling guide](https://docs.perplexity.ai/docs/sdk/error-handling.md) covers the SDK exception types and recovery patterns.

> [accordion] Where Can I Check API Status and Incidents?
>
> Current API availability and incident history are on the [System Status page](https://docs.perplexity.ai/docs/resources/status.md). If you're seeing errors that aren't explained there, reach out through the support channels below.

## Data, Privacy & Security

> [accordion] Will User Data Submitted Through the API Be Used for Model Training or Other Purposes?
>
> We collect the following types of information:
>
> **API Usage Data:** We collect limited usage metadata, such as request and token counts, model used, timestamps, duration, and API key, to operate and bill the service. If you're an Admin, you can view your project's usage on the [Billing page](https://console.perplexity.ai/project/billing) in the API Console. Members cannot view usage metrics in the console.
>
> **User Account Information:** When you create an account with us, we collect your name, email address, and other relevant contact information.
>
> Under the [API Terms of Service](https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service), Perplexity does not use Customer Content to train generative AI models. Retention depends on the API, model, and account configuration, and Zero Data Retention (ZDR) is not the default. See [Privacy & Security](https://docs.perplexity.ai/docs/resources/privacy-security.md) for details.

> [accordion] What Security and Compliance Certifications Does the API Have?
>
> Perplexity maintains a **SOC 2 Type II** report, a **2025 HIPAA gap assessment**, and a **CAIQlite** cloud security assessment. These reports, along with data-processing and other compliance documentation (for example, for DPA or GDPR requests), are available through the [Perplexity Trust Center](https://trust.perplexity.ai/). See [Privacy & Security](https://docs.perplexity.ai/docs/resources/privacy-security.md) for an overview, or [contact us](mailto:api@perplexity.ai) for documents not published there.

## Support & Reliability

> [accordion] How Do I File a Bug Report and What Happens Afterward?
>
> To file a bug report, create a new post in the [Bug Reports](https://community.perplexity.ai/c/bug-reports/10) category of the Community Forum. Include the request you sent, the response or error you got, and what you expected.
>
> The team reviews new reports and replies in the thread. Response times vary with report volume.

> [accordion] How Do I Request a New Feature?
>
> A Feature Request is a suggestion to improve or add new functionality to the Perplexity API Platform, such as:
>
> * Requesting support for a new model or capability (e.g., image processing, fine-tuning options)
> * Asking for new API parameters (e.g., additional filters, search options)
> * Suggesting performance improvements (e.g., faster response times, better citation handling)
> * Enhancing existing API features (e.g., improving streaming reliability, adding new output formats)
>
> To submit one, create a post in the [Feature Requests](https://community.perplexity.ai/c/ideas/11) category of the Community Forum, or upvote an existing request. See [Feature Requests](https://docs.perplexity.ai/docs/resources/feature-roadmap.md) for details.

> [accordion] What's the Best Way to Stay Up to Date with API Updates?
>
> We email users about new developments and also post in the [changelog](https://docs.perplexity.ai/docs/resources/changelog.md).

> [accordion] Does Perplexity Provide Service Quality Assurances Such as Service Uptime, Frequency of Failures, and Target Recovery Time in the Event of a Failure?
>
> We do not guarantee this at the moment.

> [accordion] I Have Another Question or an Issue
>
> Post your question on the [Community Forum](https://community.perplexity.ai/). For account, billing, or technical issues you can't share publicly, email [api@perplexity.ai](mailto:api@perplexity.ai). See [Get in Touch](https://docs.perplexity.ai/docs/resources/discussions.md) for the right channel for each type of request.
