@coder/ai-sdk-provider weekly downloads statistics

@coder/ai-sdk-provider

A Vercel AI SDK provider that routes requests through your Coder deployment's AI Gateway (formerly "AI Bridge"). Use any model your deployment proxies, the same way you'd use OpenRouter or any other provider.

Why: in centralized mode (the default), developers authenticate with their Coder token and never handle raw provider keys. AI Gateway authenticates each request against a Coder identity, injects the centrally managed keys for the upstream providers (Anthropic, OpenAI, Bedrock, Copilot, …), and audits usage per user. In bring-your-own-key mode, developers supply their own upstream key instead (see Authentication). The deployment decides which models and providers are available.

[!TIP] This package is for plain model calls: generateText, streamText, and generateObject (schema-constrained structured output). For Coder's server-side agent (multi-step tool loop, built-in tools, MCP servers, workspace file/shell tools), use @coder/ai-sdk-agent. They compose: provider for pure text/JSON steps, Agent for tool-driven ones.

Install

Requirements:

• Node ≥ 22 and ai v7. • A Coder deployment with AI Gateway enabled: stable since Coder v2.29, GA in v2.30, on by default in v2.34. Requires the AI Governance Add-On.

Named providers and the two wire protocols

Coder admins define AI Gateway providers: named routes on the deployment (/api/v2/aibridge//v1/…). Each speaks one of two wire protocols, set by its admin-configured type:

| Wire protocol | Provider types behind it | Default name |

| OpenAI-compatible | openai, azure, google, copilot, openai-compat, openrouter, vercel | openai | | Anthropic-compatible | anthropic (native Claude), bedrock (Bedrock-hosted Claude) | anthropic |

Routing is by URL path, not by model id: the provider name in the URL decides which upstream handles the request.

createCoder fronts the default openai / anthropic pair. The bare call coder(modelId) picks one by heuristic: ids starting with claude or anthropic go to the Anthropic-protocol provider, everything else to the OpenAI-protocol one. Explicit accessors override the heuristic, e.g. to reach Claude through a Copilot-typed provider on the OpenAI protocol:

Model ids pass through unchanged to the upstream provider (no vendor/model namespacing). Use whatever ids your deployment's providers accept.

Custom-named providers

Provider names are admin-chosen and match ^[a-z0-9]+(-[a-z0-9]+)*$. A deployment may expose, say, an Azure-backed azure-openai next to a Bedrock-backed anthropic-bedrock. There are two ways to reach them.

Sub-provider accessors. openaiProvider(name) / anthropicProvider(name) return a full sub-provider bound to that gateway provider, so one createCoder instance can target any number of providers. Pick the accessor that matches the provider's wire protocol:

| Name | Fails with |

| Outside the gateway's grammar | AI SDK InvalidArgumentError at accessor time | | Well-formed but not configured on deployment | The gateway's 404 at request time |

A name outside the grammar can never be registered, so it fails early.

Re-pointing the defaults. If your deployment just names its one OpenAI/Anthropic pair differently, override the names once and keep using the bare call and the openai / anthropic accessors:

Ask your Coder admins for provider names. Discovery is admin-only server-side: GET /api/v2/ai/providers returns 403 for regular users, and the models endpoint does not attribute models to providers.

Embeddings are not supported yet

coder.textEmbeddingModel(id) and the embedding accessors on coder.openai throw the AI SDK's NoSuchModelError immediately.

Why embeddings throw instead of sending a request

AI Gateway does not intercept /v1/embeddings, so a request would be rejected with a 404. Throwing up front avoids emitting it. The accessors stay so they can light up without a breaking change once the gateway adds an embeddings route. See coder/ai-sdk#69.

Authentication

| Mode | Set | Upstream provider key |

| Centralized (default) | apiKey: your Coder API token | Held by AI Gateway, which brokers the call | | Bring-your-own-key | coderToken: Coder token; apiKey: your upstream key | Yours, forwarded to the upstream |

Centralized mode is all most apps need:

BYOK sends coderToken in the X-Coder-AI-Governance-Token header to authenticate you to the gateway, and forwards apiKey to the upstream:

Configuration

| Option | Type | Default | Description |

| baseURL | string | — (required) | Your Coder deployment URL, e.g. https://coder.example.com. The AI Gateway path is appended for you. | | apiKey | string | — | Coder API token (centralized) or upstream key (BYOK). | | coderToken | string | — | Enables BYOK mode; sent in X-Coder-AI-Governance-Token. | | headers | Record | — | Extra headers merged into every request. | | aiGatewayPath | string | /api/v2/aibridge | Override if your deployment uses a different mount path. Use the canonical /api/v2/ai-gateway with Coder v2.35.0+. | | providers | { openai?, anthropic? } | openai / anthropic | Re-point the default pair at differently-named providers. | | fetch | typeof fetch | global fetch | Custom fetch (testing / middleware). |

Enterprise governance & security

The full reference for security reviewers is in docs/security.md: data flow, credential isolation, audit capture, required permissions, and a security FAQ.

Key points:…

Description from the npm listing.