Realtime TTS-2 is live. Built for realtime conversation that feels human. Read the Realtime TTS-2 announcement

ModelService

List models

List the models available through Inworld Inference, with their capabilities, pricing, and specifications.

GET/llm/v1alpha/models

Browse inworld.ai/models without an API key. To get model metadata through this endpoint, use Authorization: Basic $INWORLD_API_KEY. Requests without credentials return 401.

Use this endpoint to list models. The OpenAI-style GET https://api.inworld.ai/v1/models (client.models.list() in the OpenAI SDK) is not available.

The optional provider and model query parameters filter by exact match, for example ?provider=openai. For an Inworld-hosted model, combine model with provider=inworld.

By default, the list contains models you can call with chat completions. Add ?output_modalities=video for video models or ?output_modalities=decisions for decision models.

Authorizations

Authorizationstringrequired

Your authentication credentials. For Basic authentication, please populate Basic $INWORLD_API_KEY. You can create a key in one command with the Inworld CLI: inworld workspace add-key.

Query Parameters

providerstring

Return only models from this provider. Must match the model's provider value exactly (for example, openai).

modelstring

Return only the model with this exact model value (for example, gpt-5.4). Combine with provider to select a single provider's listing. For an Inworld-hosted model, set provider=inworld.

output_modalitiesstring

Return only models whose spec.outputModalities includes one of these values: text, image, video or decisions. Separate several values with commas, or pass all to list every model. Without it, the response lists the models you can call with chat completions; video and decision models are listed only when you ask for them (for example, ?output_modalities=video).

Response

200 - application/json

modelsobject[]

The list of available models.

Show child attributes

modelstringrequired

The model identifier. Combine it with provider as provider/model in the model field of Router requests. Models hosted by Inworld are listed as models/<name> (use inworld/models/<name>).

providerstringrequired

The service provider hosting the model, such as openai, anthropic, or google.

modelCreatorstring

The organization that created the model. May differ from the provider (e.g., a Meta model hosted on Groq).

pricingobject

Per-token pricing information for the model (in USD). Fields without a price are omitted.

Show child attributes

promptTokennumber

Cost per input (prompt) token in USD.

completionTokennumber

Cost per output (completion) token in USD.

promptCacheReadTokennumber

Cost per input token read from the prompt cache, in USD.

promptCacheWriteTokennumber

Cost per input token written to the prompt cache, in USD.

specobject

Technical specifications and capabilities of the model.

Show child attributes

inputModalitiesenum<string>[]

The input modalities supported by the model.

outputModalitiesenum<string>[]

The output modalities supported by the model.

contextLengthinteger

The maximum number of tokens the model can process as input (context window size).

maxCompletionTokensinteger

The maximum number of tokens the model can generate in a single response.

supportedParametersstring[]

The generation parameters supported by this model. Common values include: max_tokens, temperature, top_p, stop, seed, response_format, structured_outputs, tools, tool_choice, reasoning, include_reasoning, frequency_penalty, presence_penalty.

capabilitiesobject

High-level capability flags for the model. Only capabilities that are true are included in the response.

Show child attributes

functionCallingboolean

Whether the model supports function/tool calling.

reasoningboolean

Whether the model supports chain-of-thought reasoning.

promptCachingboolean

Whether prompt caching is available for this model.

responseSchemaboolean

Whether the model supports structured output with a response schema (JSON mode).

visionboolean

Whether the model supports image/vision input.

reasoningCapabilityobject

Reasoning support in detail. Present when the model supports reasoning.

Show child attributes

supportedboolean

Whether the model supports reasoning.

supportedLevelsenum<string>[]

The reasoning effort levels the model accepts.

responseFormatCapabilityobject

Structured output support in detail. Present when the model supports JSON output.

Show child attributes

jsonboolean

Whether the model supports JSON mode (response_format: {"type": "json_object"}).

jsonSchemaboolean

Whether the model supports strict structured output with a JSON schema.

deprecationDatestring

The date the model is scheduled to be deprecated, when announced.

isSupportedboolean

Indicates whether this model is currently supported and recommended for use. Omitted when false; such models may be experimental, deprecated, or not yet generally available.

healthobject

Recent reliability and latency statistics for the model. Omitted when no data is available.

Show child attributes

successRatenumber

Fraction of recent requests that succeeded, from 0 to 1.

avgLatencyMsstring

Average request latency in milliseconds. Returned as a string (64-bit integer JSON encoding).

p95LatencyMsstring

95th percentile request latency in milliseconds. Returned as a string (64-bit integer JSON encoding).