---
title: "Get available models (OpenAI-compatible)"
method: GET
path: "/ai/openai/models"
tags: ["OpenAI Chat"]
---

# Get available models (OpenAI-compatible)

`GET /ai/openai/models`

Lists every model currently available to your account on Telnyx Inference, including SOTA open-source LLMs hosted on Telnyx GPUs (for example `moonshotai/Kimi-K2.6`, `zai-org/GLM-5.1-FP8`, and `MiniMaxAI/MiniMax-M2.7`), embedding models, and any fine-tuned models you have created.

Each entry is a `ModelMetadata` object describing the model id, owner, task, context length, supported languages, billing tier, pricing per 1M tokens, deployment regions, and whether the model supports vision or fine-tuning. Use this endpoint to discover model ids you can pass to `POST /v2/ai/openai/chat/completions`.

Model ids follow the `{organization}/{model_name}` convention from Hugging Face (for example `moonshotai/Kimi-K2.6`). This endpoint is OpenAI-compatible: clients pointed at `https://api.telnyx.com/v2/ai/openai` can call `client.models.list()` to retrieve the same payload.

## Response `200`

Successful Response

- ModelsResponse
  - `object` string
  - `data` ModelMetadata[], required
    - `id` string, required — Model identifier. For open-source models, follows the `{organization}/{model_name}` convention from Hugging Face (e.g. `moonshotai/Kimi-K2.6`).
    - `object` string — Object type. Always `model`.
    - `created` string, date-time, required — Timestamp at which the model was registered on Telnyx Inference (ISO 8601).
    - `base_model` string, nullable — Base model the fine-tuned model was trained from. Only set for fine-tuned models.
    - `owned_by` string, required — Owner of the model. `Telnyx` for Telnyx-hosted open-source models, the upstream provider name for proxied models, or the Telnyx organization id for fine-tuned models.
    - `organization` string, required — Organization that originally published the model, matching the prefix of `id` for open-source models.
    - `task` string — Primary task the model is intended for, e.g. `text-generation`, `audio-text-to-text`, `feature-extraction` (embeddings).
    - `context_length` integer, required — Maximum total tokens (prompt + completion) supported by the model in a single request.
    - `max_completion_tokens` integer, nullable — Maximum number of completion (output) tokens the model will generate per request. `null` if unconstrained beyond `context_length`.
    - `languages` string[], required — ISO language codes the model supports (e.g. `en`, `es`).
    - `parameters` integer, required — Total parameter count of the model.
    - `parameters_str` string, nullable — Human-readable parameter count, e.g. `1.0T`, `753.9B`, `8B`.
    - `tier` 'small' | 'medium' | 'large' | 'unlisted', required — Billing tier the model belongs to. Used together with `pricing` to determine cost per 1M tokens.
    - `license` string, required — License the model is distributed under, e.g. `Apache 2.0`, `MIT`, `Llama 3 Community License`.
    - `is_fine_tunable` boolean — Whether the model can be used as a base for a fine-tuning job via `POST /v2/ai/fine_tuning/jobs`.
    - `recommended_for_assistants` boolean — Whether Telnyx currently recommends this model as the LLM powering a Telnyx AI Assistant.
    - `is_vision_supported` boolean — Whether the model accepts image inputs in chat completions (multimodal vision support).
    - `description` string, nullable — Short, human-readable summary of what the model is best suited for.
    - `pricing` object — Mapping of token kind to price, as strings to preserve precision. Typical keys are `prompt`, `cached_prompt`, and `completion`. When pricing is available the block also includes `currency` (ISO 4217 code matching the account's configured billing currency) and `unit` (the denomination the prices are quoted in, currently always `1M_tokens` for token-priced models).
    - `regions` string[] — Public region names where the model is currently deployed (e.g. `us-central-1`, `eu-central-1`).
    - `service_tiers` string[] — Service tiers supported by this Telnyx-hosted model. Use one of these values as `service_tier` in Chat Completions or Responses requests. This field is omitted for externally hosted models.

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/team-telnyx/apis/telnyx-api-2.md) · [All operations](https://skmtc.net/team-telnyx/apis/telnyx-api-2/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/team-telnyx/telnyx-api-2/revisions/8f5f4e537994/schema)