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=image for image models, ?output_modalities=video for video models, ?output_modalities=decisions for decision models or ?output_modalities=extractions for extraction models.

Each model's id is the value to send as model in a request, such as inworld/models/<name> for a model Inworld hosts; send it unchanged.

Each model's endpoints lists the request paths that serve it. To list only the models an API serves, send that path, such as ?endpoints=/v1/responses. Image models served by the Images API list /v1/images/generations; to list only those, send ?output_modalities=image&endpoints=/v1/images/generations.

A video model's entry carries spec.video, the values POST /v1/videos accepts for it (lengths, resolutions, aspect ratios, frames and reference limits), and pricing.video, its per-second prices. See Model compatibility.

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, decisions or extractions. 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 models, decision models, extraction models and models served by the Images API are listed only when you ask for them (for example, ?output_modalities=image).

endpointsstring

Return only models that every listed request path serves, spelled as in a model's endpoints, such as /v1/images/generations. Separate several paths with commas. It applies together with output_modalities: to list Images API models, send ?output_modalities=image&endpoints=/v1/images/generations. A path that takes no model returns 400.

Response

200 - application/json

modelsobject[]

The list of available models.

Show child attributes

modelstringrequired

The model's name at its provider. Models hosted by Inworld are listed as models/<name>. To call the model, send id as model in a request rather than this field.

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

Pricing information for the model (in USD). Text models carry per-token prices; video models carry video, and Images API models carry image, instead. 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.

videoobject

A video model's prices, in USD. Set only for video models.

Show child attributes

outputPerSecondobject[]

Price per second of generated video, one entry per resolution the model offers.

Show child attributes

resolutionstring

The resolution, as the resolution parameter names it.

pricenumber

Price per second, in USD.

inputImagenumber

Price per input image (a frame or reference image). Omitted when the model doesn't charge for input images.

referenceOutputPerSecondobject[]

Price per second of generated video for a job that carries input_references, where the model prices those jobs separately from outputPerSecond. Omitted when it doesn't.

Show child attributes

resolutionstring

The resolution, as the resolution parameter names it.

pricenumber

Price per second, in USD.

inputVideoPerSecondobject[]

Price per second of reference video a job carries, at the job's output resolution. Omitted when the model doesn't charge for reference videos.

Show child attributes

resolutionstring

The resolution, as the resolution parameter names it.

pricenumber

Price per second, in USD.

imageobject

An Images API model's price, in USD. Set only for models served on /v1/images/generations; a chat model that also outputs images is priced per token instead.

Show child attributes

outputImagenumber

Price per image returned, for generations and edits alike.

specobject

Technical specifications and capabilities of the model.

Show child attributes

inputModalitiesenum<string>[]

The input modalities supported by the model. file means PDF documents. For decision models, image, file, audio and video are the input types the Decisions API accepts in state.

outputModalitiesenum<string>[]

The output modalities supported by the model. Decision models report decisions.

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 catalog lists JSON mode (response_format: {"type": "json_object"}) for the model. It isn't a guarantee: on some models that report true, the format is dropped and the reply is ordinary text, so parse the reply before you rely on it.

jsonSchemaboolean

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

deprecationDatestring

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

videoobject

For a video model: the values POST /v1/videos accepts for it. The API checks each request against these limits. Set only for video models.

Show child attributes

supportedSecondsinteger[]

Every clip length the model makes (seconds), in whole seconds, ascending. A range lists each second of it.

defaultSecondsinteger

The length used when a request sets no seconds.

supportedResolutionsobject[]

The output resolutions the model makes (resolution), lowest first.

Show child attributes

resolutionstring

The resolution, as the resolution parameter names it.

supportedAspectRatiosstring[]

The aspect ratios the model makes at this resolution: all of supportedAspectRatios, or fewer. Omitted means all of them. A job with frame images isn't held to it: its clip takes the first frame's shape.

defaultResolutionstring

The resolution used when a request sets none.

supportedAspectRatiosstring[]

Every aspect ratio (aspect_ratio) the model makes at some resolution.

defaultAspectRatiostring

The aspect ratio used when a request sets none.

maxPromptCharsinteger

The longest prompt the model takes, in characters (Unicode code points). Omitted when the model sets no maximum.

minPromptCharsinteger

The shortest prompt the model takes, in characters (Unicode code points). Omitted when the model sets no minimum.

supportedFrameImagesenum<string>[]

The frame_images frame types the model takes. Empty or omitted when it takes no frames. Frames can't be combined with references.

inputReferencesobject

The reference media (input_references) a request may carry. Omitted when the model takes no references.

Show child attributes

supportedTypesobject[]

One entry per reference type the model takes. A type that isn't listed is rejected.

Show child attributes

typeenum<string>

The reference type, as input_references[].type names it.

Available options:image_urlvideo_urlaudio_url

maxCountinteger

How many references of this type a request may carry.

minDurationSecondsinteger

The shortest a single reference of this type may be, in seconds. Omitted for images, or when the model sets no minimum.

maxDurationSecondsinteger

The longest a single reference of this type may be, in seconds. Omitted for images, or when the model sets no maximum.

maxTotalDurationSecondsinteger

The longest all references of this type may be together, in seconds. Omitted when the model sets no such limit.

maxTotalInputsinteger

How many references a request may carry in total. Omitted when only the per-type limits apply.

requiredOneOfstring[]

Types at least one reference must be of. For example, ["image_url", "video_url"] means audio clips can't be sent on their own. Empty or omitted when the model requires none.

audioUseenum<string>

How the model uses an audio_url reference. speech: the model voices the clip itself where the prompt quotes the words the clip says, so a person in the video can say your recording; a prompt that quotes other words gets those words in the clip's voice. voice: the model takes only the clip's voice and generates the speech itself, saying the words the prompt quotes in that voice; it never plays the clip, whatever the clip says. Omitted when the model takes no audio references or names neither use. Exact timing is not guaranteed in either case.

Available options:speechvoice

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).

endpointsstring[]

The request paths that serve this model, such as /v1/chat/completions, /v1/messages, /v1/responses, /v1/videos, /v1/images/generations or /v1/images/edits. A path not listed rejects the model. Use it to choose the API to call.

idstringrequired

The value to send as model in a request: provider and model joined by /, such as openai/gpt-4o, or inworld/models/<name> for a model Inworld hosts. Send it unchanged.