Add Openrouter Model

REQUIRED when adding OpenRouter models - provides a script that fetches accurate context, max tokens, pricing, and capabilities from the API. Use this skill whenever the user asks to add, register, or configure a new OpenRouter model. Do NOT guess model specifications—always fetch real data from the API. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

Install

Press C to copy

$ npx skillmds@latest add tomevault-io/add-openrouter-model

Installs into ~/.claude/skills (or .claude/skills inside a project). Restart Claude Code to pick it up.

＋ Add to collection

README badge

[![SkillMD](https://skillmd.com/badge/tomevault-io/add-openrouter-model.svg)](https://skillmd.com/skills/tomevault-io/add-openrouter-model)

Trust & safety

2 of 3 audits passed

Last audited Sep 19, 2026 · commit a49022d

Works with: Claude Code Claude.ai OpenAI Codex +

File contents

Add OpenRouter Model

Fetches model details from OpenRouter API and provides structured information for the agent to add the model to source/models/openrouter-provider.ts.

Usage

Run this script from this file's directory.

./add-model.js google/gemini-3-flash-preview

How It Works

Fetches model data from https://openrouter.ai/api/v1/models
Locates the exact model by the provided OpenRouter ID
Extracts and computes key information:
- Context window length (context_length)
- Max output tokens (top_provider.max_completion_tokens)
- Pricing (pricing.prompt, pricing.completion)
- Supported features (checks supported_parameters for reasoning/tool calling)
Outputs JSON with all details needed to add the model

JSON Output Format

The script outputs a JSON object wrapped in markers:

--- MODEL_DETAILS_JSON_START ---
{...}
--- MODEL_DETAILS_JSON_END ---

JSON Structure

{
  "modelKey": "gemini-3-flash-preview",
  "openrouterId": "google/gemini-3-flash-preview",
  "providerFile": "./source/models/openrouter-provider.ts",
  "registryId": "openrouter:gemini-3-flash-preview",
  "registryEntry": {
    "id": "openrouter:gemini-3-flash-preview",
    "provider": "openrouter",
    "contextWindow": 1048576,
    "maxOutputTokens": 65535,
    "defaultTemperature": 0.5,
    "promptFormat": "markdown",
    "supportsReasoning": true,
    "supportsToolCalling": true,
    "costPerInputToken": 0.0000005,
    "costPerOutputToken": 0.000003
  },
  "clientConfig": {
    "key": "gemini-3-flash-preview",
    "openrouterId": "google/gemini-3-flash-preview"
  },
  "modelInfo": {
    "id": "google/gemini-3-flash-preview",
    "name": "Gemini 3.0 Flash Preview",
    "contextLength": 1048576,
    "maxCompletionTokens": 65535,
    "pricing": {...},
    "supportedParameters": [...]
  }
}

How to Add Model to Provider File

Step 1: Add to `openrouterModels` object

In source/models/openrouter-provider.ts, find the openrouterModels const object (starts with const openrouterModels = {). Add the new model entry in alphabetical order by key:

const openrouterModels = {
  "claude-3-5-sonnet": openRouterClient("anthropic/claude-3.5-sonnet"),
  // ... existing models ...
  "gemini-3-flash-preview": openRouterClient("google/gemini-3-flash-preview"),  // ADD THIS
  "sonnet-4.5": openRouterClient("anthropic/claude-sonnet-4.5"),
  // ...
} as const;

Step 2: Add to `openrouterModelRegistry` object

Find the openrouterModelRegistry object and add the registry entry in alphabetical order by registryId:

export const openrouterModelRegistry: {
  [K in ModelName]: ModelMetadata<ModelName>;
} = {
  "openrouter:claude-3-5-sonnet": {
    id: "openrouter:claude-3-5-sonnet",
    // ... existing entry ...
  },
  // ... existing entries ...
  "openrouter:gemini-3-flash-preview": {
    id: "openrouter:gemini-3-flash-preview",
    provider: "openrouter",
    contextWindow: 1048576,
    maxOutputTokens: 65535,
    defaultTemperature: 0.5,
    promptFormat: "markdown",
    supportsReasoning: true,
    supportsToolCalling: true,
    costPerInputToken: 0.0000005,
    costPerOutputToken: 0.000003,
  },
  // ...
};

Step 3: Validate changes

Run the project's validation commands:

npm run typecheck
npm run lint
npm run format

Field Mapping Reference

JSON Field	Registry Field	Notes
`registryEntry.id`	`id`	Full registry ID
`registryEntry.provider`	`provider`	Always "openrouter"
`registryEntry.contextWindow`	`contextWindow`	Direct mapping from API
`registryEntry.maxOutputTokens`	`maxOutputTokens`	From `top_provider.max_completion_tokens`
`registryEntry.defaultTemperature`	`defaultTemperature`	Inferred from model ID (-1 for code models)
`registryEntry.promptFormat`	`promptFormat`	Inferred: gemini/claude/qwen/mistral → "markdown", gpt/openai → "xml", deepseek → "bracket"
`registryEntry.supportsReasoning`	`supportsReasoning`	Checks `supported_parameters` for `include_reasoning` or `reasoning`
`registryEntry.supportsToolCalling`	`supportsToolCalling`	Checks `supported_parameters` for `tools`
`registryEntry.costPerInputToken`	`costPerInputToken`	From `pricing.prompt`
`registryEntry.costPerOutputToken`	`costPerOutputToken`	From `pricing.completion`

Default Value Inferences

Field	Logic
`defaultTemperature`	Returns `-1` if model ID contains "codex", "coder", or "code"; otherwise `0.5`
`promptFormat`	Maps model family to format: gemini/claude/qwen/mistral/moonshotai → "markdown", gpt/openai → "xml", deepseek → "bracket", defaults to "markdown"
`maxOutputTokens`	Falls back to `context_length` if `max_completion_tokens` is not available

Error Handling

Validates model ID exists in OpenRouter API
Shows first 10 available models if ID not found
Provides clear error messages with suggestions

Examples

# Add Gemini 3 Flash Preview
./add-model.js google/gemini-3-flash-preview

# Add Claude 3.5 Sonnet
./add-model.js anthropic/claude-3-5-sonnet

# Add DeepSeek V3
./add-model.js deepseek/deepseek-v3.2

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: add-openrouter-modeldescription: REQUIRED when adding OpenRouter models - provides a script that fetches accurate context, max tokens, pricing, and capabilities from the API. Use this skill whenever the user asks to add, register, or configure a new OpenRouter model. Do NOT guess model specifications—always fetch real data from the API. Use when this capability is needed.---# Add OpenRouter ModelFetches model details from OpenRouter API and provides structured information for the agent to add the model to `source/models/openrouter-provider.ts`.## UsageRun this script from this file's directory.```bash./add-model.js google/gemini-3-flash-preview```## How It Works1. **Fetches model data** from `https://openrouter.ai/api/v1/models`2. **Locates the exact model** by the provided OpenRouter ID3. **Extracts and computes** key information: - Context window length (`context_length`) - Max output tokens (`top_provider.max_completion_tokens`) - Pricing (`pricing.prompt`, `pricing.completion`) - Supported features (checks `supported_parameters` for reasoning/tool calling)4. **Outputs JSON** with all details needed to add the model## JSON Output FormatThe script outputs a JSON object wrapped in markers:```--- MODEL_DETAILS_JSON_START ---{...}--- MODEL_DETAILS_JSON_END ---```### JSON Structure```json{ "modelKey": "gemini-3-flash-preview", "openrouterId": "google/gemini-3-flash-preview", "providerFile": "./source/models/openrouter-provider.ts", "registryId": "openrouter:gemini-3-flash-preview", "registryEntry": { "id": "openrouter:gemini-3-flash-preview", "provider": "openrouter", "contextWindow": 1048576, "maxOutputTokens": 65535, "defaultTemperature": 0.5, "promptFormat": "markdown", "supportsReasoning": true, "supportsToolCalling": true, "costPerInputToken": 0.0000005, "costPerOutputToken": 0.000003 }, "clientConfig": { "key": "gemini-3-flash-preview", "openrouterId": "google/gemini-3-flash-preview" }, "modelInfo": { "id": "google/gemini-3-flash-preview", "name": "Gemini 3.0 Flash Preview", "contextLength": 1048576, "maxCompletionTokens": 65535, "pricing": {...}, "supportedParameters": [...] }}```## How to Add Model to Provider File### Step 1: Add to `openrouterModels` objectIn `source/models/openrouter-provider.ts`, find the `openrouterModels` const object (starts with `const openrouterModels = {`). Add the new model entry **in alphabetical order by key**:```typescriptconst openrouterModels = { "claude-3-5-sonnet": openRouterClient("anthropic/claude-3.5-sonnet"), // ... existing models ... "gemini-3-flash-preview": openRouterClient("google/gemini-3-flash-preview"), // ADD THIS "sonnet-4.5": openRouterClient("anthropic/claude-sonnet-4.5"), // ...} as const;```### Step 2: Add to `openrouterModelRegistry` objectFind the `openrouterModelRegistry` object and add the registry entry **in alphabetical order by `registryId`**:```typescriptexport const openrouterModelRegistry: { [K in ModelName]: ModelMetadata<ModelName>;} = { "openrouter:claude-3-5-sonnet": { id: "openrouter:claude-3-5-sonnet", // ... existing entry ... }, // ... existing entries ... "openrouter:gemini-3-flash-preview": { id: "openrouter:gemini-3-flash-preview", provider: "openrouter", contextWindow: 1048576, maxOutputTokens: 65535, defaultTemperature: 0.5, promptFormat: "markdown", supportsReasoning: true, supportsToolCalling: true, costPerInputToken: 0.0000005, costPerOutputToken: 0.000003, }, // ...};```### Step 3: Validate changesRun the project's validation commands:```bashnpm run typechecknpm run lintnpm run format```## Field Mapping Reference| JSON Field | Registry Field | Notes ||------------|----------------|-------|| `registryEntry.id` | `id` | Full registry ID || `registryEntry.provider` | `provider` | Always "openrouter" || `registryEntry.contextWindow` | `contextWindow` | Direct mapping from API || `registryEntry.maxOutputTokens` | `maxOutputTokens` | From `top_provider.max_completion_tokens` || `registryEntry.defaultTemperature` | `defaultTemperature` | Inferred from model ID (-1 for code models) || `registryEntry.promptFormat` | `promptFormat` | Inferred: gemini/claude/qwen/mistral → "markdown", gpt/openai → "xml", deepseek → "bracket" || `registryEntry.supportsReasoning` | `supportsReasoning` | Checks `supported_parameters` for `include_reasoning` or `reasoning` || `registryEntry.supportsToolCalling` | `supportsToolCalling` | Checks `supported_parameters` for `tools` || `registryEntry.costPerInputToken` | `costPerInputToken` | From `pricing.prompt` || `registryEntry.costPerOutputToken` | `costPerOutputToken` | From `pricing.completion` |## Default Value Inferences| Field | Logic ||-------|-------|| `defaultTemperature` | Returns `-1` if model ID contains "codex", "coder", or "code"; otherwise `0.5` || `promptFormat` | Maps model family to format: gemini/claude/qwen/mistral/moonshotai → "markdown", gpt/openai → "xml", deepseek → "bracket", defaults to "markdown" || `maxOutputTokens` | Falls back to `context_length` if `max_completion_tokens` is not available |## Error Handling- Validates model ID exists in OpenRouter API- Shows first 10 available models if ID not found- Provides clear error messages with suggestions## Examples```bash# Add Gemini 3 Flash Preview./add-model.js google/gemini-3-flash-preview# Add Claude 3.5 Sonnet./add-model.js anthropic/claude-3-5-sonnet# Add DeepSeek V3./add-model.js deepseek/deepseek-v3.2```---> Converted and distributed by [TomeVault](https://tomevault.io/claim/travisennis) — claim your Tome and manage your conversions.

tomevault-io/skills-registry/tree/main/travisennis--acai-ts--add-openrouter-model commit a49022d373

Frequently asked questions

npx skillmds@latest add tomevault-io/add-openrouter-model