> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt # Linking Fireworks AI as a source Canonical URL: https://posthog.com/docs/data-pipelines/sources/fireworks-ai > **Cloud region:** This page uses US Cloud hosts. For an EU Cloud project, use `https://eu.posthog.com` instead of `https://us.posthog.com` or `https://app.posthog.com` (app host for links). ## On this page - [Prerequisites](#prerequisites) - [Adding a data source](#adding-a-data-source) - [Sync modes](#sync-modes) - [Configuration](#configuration) - [Supported tables](#supported-tables) - [Troubleshooting](#troubleshooting) ![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_9608fcca70) ![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_dark_a92b0e022d) Let AI connect your sources for you Skip the manual setup — run this in your project and the wizard auto-detects your databases and APIs and connects them to PostHog. `npx @posthog/wizard warehouse` ![PostHog Wizard hedgehog](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png) ![](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png)Let AI connect your sources for you The Fireworks AI connector syncs models, datasets, deployments, and more into the PostHog data warehouse, so you can analyze them alongside your product data. ## Prerequisites Credentials that can read the data you want to sync. PostHog only reads data, so read access is enough. ## Adding a data source 1. In PostHog, go to the [Sources tab](https://app.posthog.com/data-management/sources) of the data pipeline section. 2. Click **\+ New source** and click **Link** next to this source. 3. Enter your credentials (see [Configuration](#configuration) below) and click **Next**. 4. Select the tables you want to sync, choose a sync method and frequency, then click **Import**. Once the syncs are complete, you can start querying this data in PostHog. Enter your Fireworks AI API key and account ID to sync your models, datasets, deployments, fine-tuning jobs, batch inference jobs, evaluations, and account users. You can find or create an API key in your [Fireworks AI account settings](https://app.fireworks.ai/settings/users/api-keys). Your account ID is shown in your account settings and in every resource name (`accounts//...`). You'll be asked for: - **API key** - **Account ID**: for example `my-account`. ## Sync modes Each table can be synced in one of several modes, depending on what the source supports: - **Webhook** (when available) – the source pushes changes to PostHog in real time. Fastest freshness, lowest ongoing cost, and the only mode that reliably captures updates and deletes. - **Incremental** – only new or updated rows are synced on each run, using a cursor field (such as an `updated_at` timestamp). Cheaper than a full refresh, but deletes aren't captured. - **Append only** – new rows are appended using a cursor field; existing rows are never updated. Ideal for immutable, append-only tables like event logs. - **Full refresh** – the whole table is reloaded on every sync. Use it when a table has no reliable cursor or when you need deletions reflected. See [sync methods](https://posthog.com/docs/data-pipelines/sources.md#sync-methods) for a full explanation of how each mode works and how to choose between them. All Fireworks AI tables are full refresh. Each sync replaces the contents of the table. ## Configuration | Option | Type | Required | | --- | --- | --- | | `API key` | password | Yes | | `Account ID` | text | Yes | ## Supported tables | Table | Description | Sync method | Incremental field | Primary key | | --- | --- | --- | --- | --- | | `models` | Models available in your Fireworks AI account, including base models and fine-tuned (PEFT addon) models. | Full refresh | — | name | | `datasets` | Datasets uploaded to or generated in your Fireworks AI account for fine-tuning and evaluation. | Full refresh | — | name | | `deployments` | Dedicated model deployments in your Fireworks AI account, including autoscaling and hardware configuration. | Full refresh | — | name | | `deployed_models` | Models loaded onto deployments (including LoRA addons), mapping each model to the deployment serving it. | Full refresh | — | name | | `routers` | Routers in your Fireworks AI account. A router distributes inference traffic across deployments for A/B testing, traffic migration, and load distribution, and is what a request's model alias resolves to. | Full refresh | — | name | | `supervised_fine_tuning_jobs` | Supervised fine-tuning (SFT) jobs run in your Fireworks AI account, with training configuration and progress. | Full refresh | — | name | | `reinforcement_fine_tuning_jobs` | Reinforcement fine-tuning (RFT) jobs run in your Fireworks AI account, with training/rollout configuration and progress. | Full refresh | — | name | | `reinforcement_fine_tuning_steps` | Reinforcement fine-tuning steps (RLOR trainer jobs) in your Fireworks AI account. Each row is one training step under a reinforcement fine-tuning job, so the table holds the per-step progression behind a job's outcome. | Full refresh | — | name | | `dpo_jobs` | Preference optimization (DPO and ORPO) fine-tuning jobs in your Fireworks AI account, the third job type alongside supervised and reinforcement fine-tuning. | Full refresh | — | name | | `batch_inference_jobs` | Batch inference jobs run in your Fireworks AI account, mapping input datasets to output datasets. | Full refresh | — | name | | `evaluation_jobs` | Evaluation jobs run in your Fireworks AI account, scoring a dataset with an evaluator. | Full refresh | — | name | | `evaluators` | Evaluators defined in your Fireworks AI account, used to score fine-tuning rollouts and evaluation jobs. | Full refresh | — | name | | `users` | Users and service accounts with access to your Fireworks AI account. | Full refresh | — | name | | `account_usage` | Daily token and spend usage for your Fireworks AI account, from the billingUsage report. One row is one usage bucket for one day. `usageCategory` names which billed surface the row measures, and the columns a row fills depend on it: serverless rows carry token counts, dedicated rows carry accelerator seconds, and training rows carry whichever the job type bills on. | Incremental, Full refresh | startTime | id | ## Troubleshooting - If the connection fails with an authorization error, the API key is wrong, expired, or has been revoked. Create a new one, then reconnect the source. - If a table syncs no rows, the credential may not have access to that data. Check its permissions, then reconnect the source. If your sync is failing or data looks wrong, see the [Data warehouse troubleshooting guide](https://posthog.com/docs/data-warehouse/troubleshooting.md). If that doesn't help, [contact support](https://us.posthog.com/#panel=support%3Asupport%3Adata_warehouse%3A%3Atrue) – we're happy to help.