Models - NanoGPT API Documentation

cURL

curl --request GET \
  --url https://nano-gpt.com/api/v1/models \
  --header 'Authorization: Bearer <token>'

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-5.2",
      "object": "model",
      "created": 123,
      "owned_by": "openai",
      "name": "GPT-4o Mini",
      "description": "OpenAI's affordable and intelligent small model for fast, lightweight tasks",
      "context_length": 128000,
      "pricing": {
        "prompt": 0.00015,
        "completion": 0.0006,
        "currency": "USD",
        "unit": "per_million_tokens"
      },
      "distillationPolicy": {
        "status": "allowed",
        "label": "License permits distillation",
        "basis": "permissive-open-weights",
        "sourceUrl": "https://example.com/license-or-terms",
        "note": "Short explanation of the policy signal."
      }
    }
  ]
}

GET

models

cURL

curl --request GET \
  --url https://nano-gpt.com/api/v1/models \
  --header 'Authorization: Bearer <token>'

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-5.2",
      "object": "model",
      "created": 123,
      "owned_by": "openai",
      "name": "GPT-4o Mini",
      "description": "OpenAI's affordable and intelligent small model for fast, lightweight tasks",
      "context_length": 128000,
      "pricing": {
        "prompt": 0.00015,
        "completion": 0.0006,
        "currency": "USD",
        "unit": "per_million_tokens"
      },
      "distillationPolicy": {
        "status": "allowed",
        "label": "License permits distillation",
        "basis": "permissive-open-weights",
        "sourceUrl": "https://example.com/license-or-terms",
        "note": "Short explanation of the policy signal."
      }
    }
  ]
}

Overview

The /api/v1/models endpoint provides a list of available text generation models. It supports optional detailed information including pricing data. The endpoint maintains full backwards compatibility while adding powerful new features. For non-text model catalogs, use the dedicated catalog endpoints:

For API-only distillation metadata and filtering, see Distillation Policy.

Notable Model IDs (Examples)

Model availability changes frequently. Use GET /api/v1/models as the authoritative source of callable IDs. Examples below use canonical IDs only; legacy aliases are intentionally omitted.

OpenAI: openai/gpt-5.2, openai/gpt-5.2-codex, openai/gpt-5.2-pro
Anthropic: anthropic/claude-opus-4.6, anthropic/claude-opus-4.6:thinking, anthropic/claude-sonnet-4.6, anthropic/claude-sonnet-4.6:thinking
Google Gemini 3: google/gemini-3-flash-preview, google/gemini-3.1-pro-preview, gemini-3-pro-image-preview, google/gemini-3-flash-preview-thinking
xAI Grok: x-ai/grok-4.3, x-ai/grok-latest, x-ai/grok-4.20, x-ai/grok-4.20-multi-agent
Moonshot Kimi K2.5: moonshotai/kimi-k2.5, moonshotai/kimi-k2.5:thinking
Zhipu GLM 4.6 / 4.7: z-ai/glm-4.6, z-ai/glm-4.6:thinking, zai-org/glm-4.7, zai-org/glm-4.7:thinking
DeepSeek V3.2: deepseek/deepseek-v3.2, deepseek/deepseek-v3.2:thinking, deepseek/deepseek-v3.2-speciale
Qwen3 Coder: qwen/qwen3-coder-next, qwen/qwen3-coder-plus, qwen/qwen3-coder-flash
NousResearch Hermes 4: nousresearch/hermes-4-405b, nousresearch/hermes-4-405b:thinking, nousresearch/hermes-4-70b

Compatibility

Responses mirror OpenAI’s Models API shape. All models endpoints return:

{
  "object": "list",
  "data": [ { /* model */ }, ... ]
}

Each model minimally includes:

{
  "id": "openai/gpt-5.2",
  "object": "model",
  "created": 1736966400,
  "owned_by": "openai"
}

Features

Basic Mode: Standard OpenAI-compatible model listing
Detailed Mode: Enhanced information with pricing and model descriptions

Provider Selection Discovery

Provider selection support and provider IDs are discovered via GET /api/models/:canonicalId/providers. See Provider Selection for details.

Query Parameters

Parameter	Type	Default	Description
`detailed`	boolean	`false`	Returns detailed model information including pricing and capabilities
`sort`	string	none	Values: `favorites`, `mostused`. Reorders the returned model list. Sorting only affects models that would already be visible to the caller. It does not add or hide models.

When detailed=true, additional fields may be included per model:

name — display name
description — short model description
context_length — max input tokens (if known)
max_output_tokens — max output tokens (if known)
capabilities — feature flags (see below)
pricing.prompt and pricing.completion — at-cost per-million-token pricing in USD
pricing.unit — per_million_tokens
icon_url — small icon representing the provider
cost_estimate — internal rollup used in UI for cost hints (for example "$", "$$", or an object)
category — optional category tag (for example "flagship", "mini", "reasoning")
distillationPolicy — optional policy metadata indicating whether model outputs may be used for distillation or output-based training under NanoGPT’s recorded model-license rules

Sorting model lists

GET /api/v1/models supports sort=favorites and sort=mostused. When sort is present, NanoGPT returns the same model list the caller would normally receive, but reordered by the selected ranking. Sorting only affects models that would already be visible to the caller. It does not add or hide models.

sort=favorites: Orders models by the authenticated account’s recent model usage.
sort=mostused: Orders models by global completed model usage.
Unused or unranked models remain in the response after ranked models, in the normal catalog order.
sort=favorites requires a valid API key to personalize the order. If no valid API key is provided, it falls back to normal ordering.
sort=mostused does not require authentication.
Invalid sort values are ignored.
Can be combined with detailed=true.

Examples:

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/v1/models?sort=favorites"

curl "https://nano-gpt.com/api/v1/models?sort=mostused"

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/v1/models?detailed=true&sort=favorites"

curl "https://nano-gpt.com/api/v1/models?detailed=true&sort=mostused"

`capabilities` (detailed mode)

Common capability flags:

Field	Type	Description
`vision`	boolean	Supports image inputs
`reasoning`	boolean	Supports extended thinking/reasoning
`tool_calling`	boolean	Supports function/tool calling
`parallel_tool_calls`	boolean	Supports multiple tool calls in parallel
`structured_output`	boolean	Supports structured/JSON output modes
`pdf_upload`	boolean	Supports PDF/document inputs

Authentication

Authentication is optional but enables user-specific pricing in detailed mode:

Header	Format	Required	Description
`Authorization`	`Bearer {api_key}`	Optional	API key for user-specific pricing
`x-api-key`	`{api_key}`	Optional	Alternative API key header

Notes:

Invalid or missing API keys still return a list of models. We simply omit user-specific pricing considerations in detailed=true mode.
With a valid key, the canonical /api/v1/models may apply your account’s subscription visibility preference (see Endpoint Variants).

Response Formats

Basic Response (Default)

Standard OpenAI-compatible format without pricing information:

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-5.2",
      "object": "model",
      "created": 1704067200,
      "owned_by": "openai"
    },
    {
      "id": "anthropic/claude-opus-4.6",
      "object": "model", 
      "created": 1704067200,
      "owned_by": "anthropic"
    }
  ]
}

Detailed Response

Enhanced format with model descriptions, context lengths, and pricing:

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-5.2",
      "object": "model",
      "created": 1704067200,
      "owned_by": "openai",
      "name": "GPT-5.2",
      "description": "OpenAI's flagship general-purpose model",
      "context_length": 128000,
      "max_output_tokens": 16384,
      "capabilities": {
        "vision": true,
        "reasoning": false,
        "tool_calling": true,
        "parallel_tool_calls": true,
        "structured_output": true,
        "pdf_upload": true
      },
      "pricing": {
        "prompt": 2.50,
        "completion": 10.00,
        "currency": "USD",
        "unit": "per_million_tokens"
      },
      "icon_url": "/icons/OpenAI.svg",
      "cost_estimate": "$",
      "category": "flagship"
    },
    {
      "id": "anthropic/claude-opus-4.6",
      "object": "model",
      "created": 1704067200,
      "owned_by": "anthropic",
      "name": "Claude Opus 4.5",
      "description": "Anthropic's top-tier model for deep reasoning and writing",
      "context_length": 200000,
      "max_output_tokens": 8192,
      "capabilities": { "vision": true, "reasoning": true, "tool_calling": true },
      "pricing": {
        "prompt": 15.00,
        "completion": 75.00,
        "currency": "USD", 
        "unit": "per_million_tokens"
      },
      "icon_url": "/icons/Anthropic.svg",
      "cost_estimate": "$$$",
      "category": "reasoning"
    }
  ]
}

Field Descriptions

Basic Fields (Always Present)

Field	Type	Description
`id`	string	Unique model identifier
`object`	string	Always “model” for OpenAI compatibility
`created`	number	Unix timestamp of response creation
`owned_by`	string	Model provider (openai, anthropic, meta, google, etc.)

Enhanced Fields (Detailed Mode Only)

Field	Type	Description
`name`	string	Human-readable model name
`description`	string	Detailed model description
`context_length`	number	Maximum input tokens (null if not available)
`max_output_tokens`	number	Maximum output tokens (null if not available)
`capabilities`	object	Feature flags (e.g., `vision: boolean`)
`pricing`	object	Pricing information object
`icon_url`	string	Path/URL for a small provider icon
`cost_estimate`	string or object	Internal hints (for example `"$"` / `"$$"` or `{ cheap: true }`)
`category`	string	Optional category (e.g., `"flagship"`, `"mini"`, `"reasoning"`)
`distillationPolicy`	object	Optional API-only distillation metadata. See Distillation Policy.

Pricing Object Structure

Field	Type	Description
`prompt`	number	Cost per million input tokens in USD
`completion`	number	Cost per million output tokens in USD
`currency`	string	Always “USD”
`unit`	string	Always “per_million_tokens”

Distillation Policy

Where available, text model records include a distillationPolicy object with status, label, basis, sourceUrl, and note. This indicates whether model outputs may be used for model training, fine-tuning, distillation, or similar model-improvement workflows under NanoGPT’s recorded interpretation of model licenses and provider terms.

{
  "distillationPolicy": {
    "status": "allowed",
    "label": "License permits distillation",
    "basis": "permissive-open-weights",
    "sourceUrl": "https://example.com/license-or-terms",
    "note": "Short explanation of the policy signal."
  }
}

Use the explore endpoints when you need to filter for distillation-allowed text models:

GET /api/explore/text-models?distillation=allowed

GET /api/explore/search?type=text&q=qwen&distillation=allowed

The filter applies only to text models. Responses include meta.distillation: "allowed" when the filter is used and meta.distillation: "all" otherwise. Provider route policy can differ from model-level policy. Use GET /api/models/:canonicalId/providers and inspect each provider row’s distillationPolicy before relying on a specific route for distillation. This metadata is informational and is not legal advice. Provider terms and model licenses can change, and licenses may impose attribution, naming, acceptable-use, or derivative-model restrictions even when distillation is allowed.

Usage Examples

Basic Request

curl "https://nano-gpt.com/api/v1/models"

Detailed Request

curl "https://nano-gpt.com/api/v1/models?detailed=true"

Sort by Favorites

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/v1/models?sort=favorites"

Sort by Most Used

curl "https://nano-gpt.com/api/v1/models?sort=mostused"

Detailed and Sorted

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/v1/models?detailed=true&sort=favorites"

curl "https://nano-gpt.com/api/v1/models?detailed=true&sort=mostused"

Detailed with Authentication

curl "https://nano-gpt.com/api/v1/models?detailed=true" \
  -H "Authorization: Bearer your_api_key_here"

Alternative API Key Header

curl "https://nano-gpt.com/api/v1/models?detailed=true" \
  -H "x-api-key: your_api_key_here"

Endpoint Variants

In addition to the canonical /api/v1/models, two filtered variants are available:

1) GET /api/v1/models (canonical)

Returns all visible text models (excludes internal free/helper selector models except auto-model*).
If your account has an active subscription and you have not enabled “Also show paid models”, the list is automatically restricted to only subscription-included models.
If you enable “Also show paid models” in settings, it returns the full set again.

Examples:

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  https://nano-gpt.com/api/v1/models

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/v1/models?detailed=true"

2) GET /api/subscription/v1/models (subscription-only)

Always returns only models included in the NanoGPT subscription (equivalent to our isTextEligible(modelId) filter).
Ignores the user’s “Also show paid models” preference; it is always subscription-only.
Supports ?detailed=true and API key–aware, at-cost pricing metadata.

Examples:

curl https://nano-gpt.com/api/subscription/v1/models

curl -H "x-api-key: $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/subscription/v1/models?detailed=true"

3) GET /api/paid/v1/models (paid/extras)

Returns only models that are NOT part of the subscription (paid/premium/extras).
Supports ?detailed=true and API key–aware, at-cost pricing metadata.

Examples:

curl https://nano-gpt.com/api/paid/v1/models

curl -H "Authorization: Bearer $NANOGPT_API_KEY" \
  "https://nano-gpt.com/api/paid/v1/models?detailed=true"

Choosing the Right Endpoint

Use /api/subscription/v1/models for curated lists guaranteed to be subscription-included (e.g., sub-only integrations).
Use /api/paid/v1/models to focus on paid or premium models.
Use /api/v1/models for the canonical list and let the account’s “Also show paid models” preference decide visibility.

Errors and Limits

These endpoints typically return 200 with a list. If an invalid API key is provided, the list still returns and simply omits user-specific pricing considerations in detailed=true mode.
Standard CORS and rate limiting apply. In overload scenarios you may receive 429 with:

{ "code": "rate_limited", "message": "Rate limit exceeded" }

Backwards Compatibility

Default response format unchanged
All existing fields preserved
New fields are additive only
No breaking changes to existing integrations

Image models - List image model capabilities and supported parameters
Video models - List video model capabilities and supported parameters
Audio models - List text-to-speech and speech-to-text models
Embedding models - List embedding model dimensions, token limits, and pricing
/api/v1/embeddings - Create embeddings using the available embedding models
Provider Selection - Discover model providers and set provider preferences
/api/subscription/v1/models - Subscription-included text models
/api/paid/v1/models - Paid or premium text models

Notes

Scope: These endpoints list text-chat models. For image, video, audio, and embedding catalogs, use the dedicated model catalog pages linked above.
Fields are subject to change as new capabilities or providers are added. We aim to remain OpenAI-API compatible for basic consumers (id/object/created/owned_by).

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

detailed

boolean

default:false

Returns detailed model information including pricing

sort

enum<string>

Reorders the returned model list without adding or hiding models. favorites orders by the authenticated account's recent model usage and requires a valid API key; without one it falls back to normal ordering. mostused orders by global completed model usage and does not require authentication. Unused or unranked models remain after ranked models in normal catalog order. Invalid values are ignored.

Available options:

favorites,

mostused

Example:

"favorites"

Response

List of available models

object

string

default:list

Type of object, always 'list' for the models response

data

object[]

List of available models

Show child attributes

Quickstart Image Models

​Overview

​Notable Model IDs (Examples)

​Compatibility

​Features

​Provider Selection Discovery

​Query Parameters

​Sorting model lists

​capabilities (detailed mode)

​Authentication

​Response Formats

​Basic Response (Default)

​Detailed Response

​Field Descriptions

​Basic Fields (Always Present)

​Enhanced Fields (Detailed Mode Only)

​Pricing Object Structure

​Distillation Policy

​Usage Examples

​Basic Request

​Detailed Request

​Sort by Favorites

​Sort by Most Used

​Detailed and Sorted

​Detailed with Authentication

​Alternative API Key Header

​Endpoint Variants

​1) GET /api/v1/models (canonical)

​2) GET /api/subscription/v1/models (subscription-only)

​3) GET /api/paid/v1/models (paid/extras)

​Choosing the Right Endpoint

​Errors and Limits

​Backwards Compatibility

​Related Endpoints

​Notes

Authorizations

Query Parameters

Response

Overview

Notable Model IDs (Examples)

Compatibility

Features

Provider Selection Discovery

Query Parameters

Sorting model lists

`capabilities` (detailed mode)

Authentication

Response Formats

Basic Response (Default)

Detailed Response

Field Descriptions

Basic Fields (Always Present)

Enhanced Fields (Detailed Mode Only)

Pricing Object Structure

Distillation Policy

Usage Examples

Basic Request

Detailed Request

Sort by Favorites

Sort by Most Used

Detailed and Sorted

Detailed with Authentication

Alternative API Key Header

Endpoint Variants

1) GET /api/v1/models (canonical)

2) GET /api/subscription/v1/models (subscription-only)

3) GET /api/paid/v1/models (paid/extras)

Choosing the Right Endpoint

Errors and Limits

Backwards Compatibility

Related Endpoints

Notes