Compatibility

One table to answer "can I do X on Y", from what each pack actually implements.

Language models

* Rides the shared chat-completions wire; whether a given model honors it is up to the model. Perplexity has no tool calling upstream, so the library doesn't pretend otherwise.

Column notes. Structured output uses each provider's best native mechanism: JSON schema mode on the OpenAI wire, constrained decoding on Gemini, a forced tool call on Anthropic, guided generation on-device. Sources means citations surface as StreamPart.source (OpenAI url annotations, xAI live search, Perplexity and Cohere citations). Cached tokens means usage.cachedInputTokens is populated on prompt-cache hits.

Models the library special-cases

Model ids are free strings — anything the provider serves works. These are the ids the library treats specially, straight from the source:

OpenAI

• The reasoning ruleset applies to o1*, o3*, o4-mini*, and gpt-5* except gpt-5-chat*.
• gpt-5.1 through gpt-5.6 accept temperature/topP again when reasoning effort is none; other reasoning models drop them.

Anthropic

The same table drives Bedrock's anthropic.* model ids.

Google

• gemini-3* takes thinkingLevel — except gemini-3-pro-image, which stays on budgets.
• Budget models cap at 32,768 thinking tokens for 2.5 Pro and gemini-3-pro-image, 24,576 for everything else.

xAI

• grok-4.20 date-stamped -reasoning / -non-reasoning variants have their behavior baked in, so the reasoning parameter is not sent.

Mistral

• reasoning maps to reasoning_effort only on mistral-small-latest, mistral-small-2603, mistral-medium-3, and mistral-medium-3.5.

Bedrock

Three families by model-id prefix: anthropic.* gets Claude thinking config, openai.* gets reasoning_effort, and everything else gets the generic reasoningConfig (where xhigh becomes max).

Beyond text

The async transcription providers (AssemblyAI, Rev.ai, Gladia) submit, poll, and fetch internally — one call either way.

First-class models on compatible endpoints

Named services get dedicated model types with the AI SDK's exact base URLs and environment variables:

OpenAICompatibleProvider remains the general initializer for any other chat-completions endpoint. Replicate has a first-class ReplicateImageModel, but no language-model pack because its prediction API is not the chat-completions wire.