> ## Documentation Index > Fetch the complete documentation index at: https://www.edgee.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # TypeScript SDK - Send Method > Complete guide to the send() method in the TypeScript SDK. The `send()` method is used to make non-streaming chat completion requests to the Edgee AI Gateway. It returns a `Promise` with the model's response. ## Arguments The `send()` method accepts a single `SendOptions` object with the following properties: | Property | Type | Description | | ------------------------------------------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------------------------------------------------------------- | | `model` | `string` | The model identifier to use (e.g., `"openai/gpt-5.2"`) | | `input` | `string \| InputObject` | The input for the completion. Can be a simple string or a structured `InputObject` | ### Input Types #### String Input When `input` is a string, it's automatically converted to a user message: ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: 'What is the capital of France?' }); // Equivalent to: input: { messages: [{ role: 'user', content: 'What is the capital of France?' }] } console.log(response.text); // "The capital of France is Paris." ``` #### InputObject When `input` is an `InputObject`, you have full control over the conversation: | Property | Type | Description | | --------------------------------------------------------------------------------------------------------------------------------- | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `messages` | `Message[]` | Array of conversation messages | | `tools` | `Tool[]` | Array of function tools available to the model | | `tool_choice` | `ToolChoice` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/typescript/tools) for details | | `tags` | `string[]` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) | | `compression_model` | `string` | Compression model for this request: `"claude"`, `"codex"`, `"opencode"`, `"cursor"`. Each model is a bundle of compression strategies. Overrides API key settings when present. | **Example with InputObject:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: { messages: [ { role: 'user', content: 'What is 2+2?' } ] } }); console.log(response.text); // "2+2 equals 4." ``` **Example with Tags:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: { messages: [ { role: 'user', content: 'Summarize this article' } ], tags: ['summarization', 'production', 'user-123'] } }); ``` ### Message Object Each message in the `messages` array has the following structure: | Property | Type | Description | | ----------------------------------------------------------------------------------------------------------------------------- | ------------ | --------------------------------------------------------------------------------------------------------------------------------------- | | `role` | `string` | The role of the message sender: `"system"`, `"developer"`, `"user"`, `"assistant"`, or `"tool"` | | `content` | `string` | The message content. Required for `system`, `user`, `tool` and `developer` roles. Optional for `assistant` when `tool_calls` is present | | `name` | `string` | Optional name for the message sender | | `tool_calls` | `ToolCall[]` | Array of tool calls made by the assistant. Only present in `assistant` messages | | `tool_call_id` | `string` | ID of the tool call this message is responding to. Required for `tool` role messages | ### Message Roles * **`system`**: System instructions that set the behavior of the assistant * **`developer`**: Instructions provided by the application developer, prioritized ahead of user messages. * **`user`**: Instructions provided by an end user. * **`assistant`**: Assistant responses (can include `tool_calls`) * **`tool`**: Results from tool/function calls (requires `tool_call_id`) **Example - System and User Messages:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: { messages: [ { role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'What is 2+2?' }, { role: 'assistant', content: '2+2 equals 4.' }, { role: 'user', content: 'What about 3+3?' } ] } }); console.log(response.text); // "3+3 equals 6." ``` For complete tool calling examples and best practices, see [Tools documentation](/sdk/typescript/tools). ## Return Value The `send()` method returns a `Promise` with the following structure: ### SendResponse Object | Property | Type | Description | | ------------- | -------------------------- | ------------------------------------------------------ | | `choices` | `Choice[]` | Array of completion choices (typically one) | | `usage` | `Usage \| undefined` | Token usage information (if provided by the API) | | `compression` | `Compression \| undefined` | Token compression metrics (if compression was applied) | ### Choice Object Each choice in the `choices` array contains: | Property | Type | Description | | --------------- | ---------------- | ----------------------------------------------------------------------------------------------------------------------- | | `index` | `number` | The index of this choice in the array | | `message` | `Message` | The assistant's message response | | `finish_reason` | `string \| null` | Reason why the generation stopped. Possible values: `"stop"`, `"length"`, `"tool_calls"`, `"content_filter"`, or `null` | **Example - Handling Multiple Choices:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: 'Give me a creative idea.' }); // Process all choices response.choices.forEach((choice, index) => { console.log(`Choice ${index}:`, choice.message.content); console.log(`Finish reason: ${choice.finish_reason}`); }); ``` ### Message Object (in Response) The `message` in each choice has: | Property | Type | Description | | ------------ | ------------------------- | ----------------------------------------------------------------------------------------------------------------- | | `role` | `string` | The role of the message (typically `"assistant"`) | | `content` | `string \| null` | The text content of the response. `null` when `tool_calls` is present | | `tool_calls` | `ToolCall[] \| undefined` | Array of tool calls requested by the model (if any). See [Tools documentation](/sdk/typescript/tools) for details | ### Usage Object Token usage information (when available): | Property | Type | Description | | ------------------- | -------- | ------------------------------------------------------------- | | `prompt_tokens` | `number` | Number of tokens in the prompt (after compression if applied) | | `completion_tokens` | `number` | Number of tokens in the completion | | `total_tokens` | `number` | Total tokens used (prompt + completion) | **Example - Accessing Token Usage:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: 'Explain quantum computing briefly.' }); if (response.usage) { console.log(`Prompt tokens: ${response.usage.prompt_tokens}`); console.log(`Completion tokens: ${response.usage.completion_tokens}`); console.log(`Total tokens: ${response.usage.total_tokens}`); } ``` ### Compression Object Token compression metrics (when compression is applied): | Property | Type | Description | | -------------- | -------- | ------------------------------------------------------------ | | `saved_tokens` | `number` | Number of tokens saved by compression | | `cost_savings` | `number` | Estimated cost savings in micro-units (e.g. 27000 = \$0.027) | | `reduction` | `number` | Percentage reduction (e.g. 48 = 48%, may be fractional) | | `time_ms` | `number` | Time taken for compression in milliseconds | **Example - Accessing Compression Metrics:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: { messages: [ { role: 'user', content: 'Analyze this long document with lots of context...' } ], compression_model: "claude", } }); if (response.compression) { console.log(`Saved tokens: ${response.compression.saved_tokens}`); console.log(`Reduction: ${response.compression.reduction}%`); console.log(`Cost savings: $${(response.compression.cost_savings / 1_000_000).toFixed(3)}`); console.log(`Time: ${response.compression.time_ms} ms`); } ``` The `compression` object is only present when token compression is applied to the request. Simple queries may not trigger compression. ## Convenience Properties The `SendResponse` class provides convenience getters for easier access: | Property | Type | Description | | -------------- | -------------------- | ------------------------------------------- | | `text` | `string \| null` | Shortcut to `choices[0].message.content` | | `message` | `Message \| null` | Shortcut to `choices[0].message` | | `finishReason` | `string \| null` | Shortcut to `choices[0].finish_reason` | | `toolCalls` | `ToolCall[] \| null` | Shortcut to `choices[0].message.tool_calls` | **Example - Using Convenience Properties:** ```typescript theme={"dark"} const response = await edgee.send({ model: 'gpt-5.2', input: 'Hello!' }); // Instead of: response.choices[0].message.content console.log(response.text); // Instead of: response.choices[0].message console.log(response.message); // Instead of: response.choices[0].finish_reason console.log(response.finishReason); // Instead of: response.choices[0].message.tool_calls if (response.toolCalls) { console.log('Tool calls:', response.toolCalls); } ``` ## Error Handling The `send()` method can throw errors in several scenarios: ```typescript theme={"dark"} try { const response = await edgee.send({ model: 'gpt-5.2', input: 'Hello!' }); } catch (error) { if (error instanceof Error) { // API errors: "API error {status}: {message}" // Network errors: Standard fetch errors console.error('Request failed:', error.message); } } ``` ### Common Errors * **API errors**: `Error: API error {status}: {message}` - The API returned an error status * **Network errors**: Standard fetch network errors * **Invalid input**: Errors from invalid request structure