> ## Documentation Index > Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a chat completion (OpenAI-compatible) > Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK by setting the base URL to `https://api.telnyx.com/v2/ai/openai`. ## OpenAPI ````yaml https://telnyx-openapi-ng.s3.us-east-1.amazonaws.com/ai/inference.yml post /ai/openai/chat/completions openapi: 3.1.0 info: title: Telnyx AI Inference API version: 2.0.0 description: API for AI inference, including chat completions, fine-tuning, and models. contact: email: support@telnyx.com servers: - url: https://api.telnyx.com/v2 security: - bearerAuth: [] paths: /ai/openai/chat/completions: post: tags: - OpenAI Chat summary: Create a chat completion (OpenAI-compatible) description: >- Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK by setting the base URL to `https://api.telnyx.com/v2/ai/openai`. operationId: create_openai_chat_completion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' example: messages: - role: system content: You are a friendly chatbot. - role: user content: Hello, world! responses: '200': description: Successful Response content: application/json: schema: type: object additionalProperties: true '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: JavaScript source: |- import Telnyx from 'telnyx'; const client = new Telnyx({ apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted }); const response = await client.ai.openai.chat.createCompletion({ messages: [ { role: 'system', content: 'You are a friendly chatbot.' }, { role: 'user', content: 'Hello, world!' }, ], }); console.log(response); - lang: Python source: |- import os from telnyx import Telnyx client = Telnyx( api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted ) response = client.ai.openai.chat.create_completion( messages=[{ "role": "system", "content": "You are a friendly chatbot.", }, { "role": "user", "content": "Hello, world!", }], ) print(response) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/team-telnyx/telnyx-go\"\n\t\"github.com/team-telnyx/telnyx-go/option\"\n)\n\nfunc main() {\n\tclient := telnyx.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tresponse, err := client.AI.OpenAI.Chat.NewCompletion(context.TODO(), telnyx.AIOpenAIChatNewCompletionParams{\n\t\tMessages: []telnyx.AIOpenAIChatNewCompletionParamsMessage{{\n\t\t\tRole: \"system\",\n\t\t\tContent: telnyx.AIOpenAIChatNewCompletionParamsMessageContentUnion{\n\t\t\t\tOfString: telnyx.String(\"You are a friendly chatbot.\"),\n\t\t\t},\n\t\t}, {\n\t\t\tRole: \"user\",\n\t\t\tContent: telnyx.AIOpenAIChatNewCompletionParamsMessageContentUnion{\n\t\t\t\tOfString: telnyx.String(\"Hello, world!\"),\n\t\t\t},\n\t\t}},\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", response)\n}\n" - lang: Java source: >- package com.telnyx.sdk.example; import com.telnyx.sdk.client.TelnyxClient; import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient; import com.telnyx.sdk.models.ai.openai.chat.ChatCreateCompletionParams; import com.telnyx.sdk.models.ai.openai.chat.ChatCreateCompletionResponse; public final class Main { private Main() {} public static void main(String[] args) { TelnyxClient client = TelnyxOkHttpClient.fromEnv(); ChatCreateCompletionParams params = ChatCreateCompletionParams.builder() .addMessage(ChatCreateCompletionParams.Message.builder() .content("You are a friendly chatbot.") .role(ChatCreateCompletionParams.Message.Role.SYSTEM) .build()) .addMessage(ChatCreateCompletionParams.Message.builder() .content("Hello, world!") .role(ChatCreateCompletionParams.Message.Role.USER) .build()) .build(); ChatCreateCompletionResponse response = client.ai().openai().chat().createCompletion(params); } } - lang: Ruby source: |- require "telnyx" telnyx = Telnyx::Client.new(api_key: "My API Key") response = telnyx.ai.openai.chat.create_completion( messages: [{content: "You are a friendly chatbot.", role: :system}, {content: "Hello, world!", role: :user}] ) puts(response) - lang: PHP source: >- ai->openai->chat->createCompletion( messages: [ ['content' => 'You are a friendly chatbot.', 'role' => 'system'], ['content' => 'Hello, world!', 'role' => 'user'], ], apiKeyRef: 'api_key_ref', bestOf: 0, earlyStopping: true, enableThinking: true, frequencyPenalty: 0, guidedChoice: ['string'], guidedJson: ['foo' => 'bar'], guidedRegex: 'guided_regex', lengthPenalty: 0, logprobs: true, maxTokens: 0, minP: 0, model: 'model', n: 0, presencePenalty: 0, responseFormat: ['type' => 'text'], seed: 0, stop: 'string', stream: true, temperature: 0, toolChoice: 'none', tools: [ [ 'function' => [ 'name' => 'name', 'description' => 'description', 'parameters' => ['foo' => 'bar'], ], 'type' => 'function', ], ], topLogprobs: 0, topP: 0, useBeamSearch: true, ); var_dump($response); } catch (APIException $e) { echo $e->getMessage(); } - lang: CLI source: |- telnyx ai:openai:chat create-completion \ --api-key 'My API Key' \ --message '{content: You are a friendly chatbot., role: system}' \ --message "{content: 'Hello, world!', role: user}" components: schemas: ChatCompletionRequest: properties: messages: items: $ref: '#/components/schemas/ChatCompletionSystemMessageParam' type: array example: - role: system content: You are a friendly chatbot. - role: user content: Hello, world! description: A list of the previous chat messages for context. model: type: string default: meta-llama/Meta-Llama-3.1-8B-Instruct description: The language model to chat with. api_key_ref: type: string description: >- If you are using an external inference provider like xAI or OpenAI, this field allows you to pass along a reference to your API key. After creating an [integration secret](https://developers.telnyx.com/api-reference/integration-secrets/create-a-secret) for you API key, pass the secret's `identifier` in this field. stream: type: boolean default: false description: >- Whether or not to stream data-only server-sent events as they become available. temperature: type: number default: 0.1 description: >- Adjusts the "creativity" of the model. Lower values make the model more deterministic and repetitive, while higher values make the model more random and creative. max_tokens: type: integer description: Maximum number of completion tokens the model should generate. tools: items: oneOf: - $ref: '#/components/schemas/ChatCompletionToolParam' - $ref: '#/components/schemas/Retrieval' type: array description: >- The `function` tool type follows the same schema as the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat). The `retrieval` tool type is unique to Telnyx. You may pass a list of [embedded storage buckets](https://developers.telnyx.com/api-reference/embeddings/embed-documents) for retrieval-augmented generation. tool_choice: type: string enum: - none - auto - required response_format: $ref: '#/components/schemas/ChatCompletionResponseFormatParam' description: >- Use this is you want to guarantee a JSON output without defining a schema. For control over the schema, use `guided_json`. guided_json: type: object description: >- Must be a valid JSON schema. If specified, the output will follow the JSON schema. additionalProperties: true guided_regex: type: string description: If specified, the output will follow the regex pattern. guided_choice: type: array items: type: string description: If specified, the output will be exactly one of the choices. min_p: type: number description: >- This is an alternative to `top_p` that [many prefer](https://github.com/huggingface/transformers/issues/27670). Must be in [0, 1]. 'n': type: number description: >- This will return multiple choices for you instead of a single chat completion. use_beam_search: type: boolean default: false description: >- Setting this to `true` will allow the model to [explore more completion options](https://huggingface.co/blog/how-to-generate#beam-search). This is not supported by OpenAI. best_of: type: integer description: >- This is used with `use_beam_search` to determine how many candidate beams to explore. length_penalty: type: number default: 1 description: >- This is used with `use_beam_search` to prefer shorter or longer completions. early_stopping: type: boolean default: false description: >- This is used with `use_beam_search`. If `true`, generation stops as soon as there are `best_of` complete candidates; if `false`, a heuristic is applied and the generation stops when is it very unlikely to find better candidates. logprobs: type: boolean default: false description: >- Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. top_logprobs: type: integer description: >- This is used with `logprobs`. An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. frequency_penalty: type: number default: 0 description: >- Higher values will penalize the model from repeating the same output tokens. presence_penalty: type: number default: 0 description: >- Higher values will penalize the model from repeating the same output tokens. top_p: type: number description: >- An alternative or complement to `temperature`. This adjusts how many of the top possibilities to consider. stop: description: >- Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. oneOf: - type: string - type: array items: type: string maxItems: 4 seed: type: integer description: >- If specified, the system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. enable_thinking: type: boolean default: true description: >- Whether to enable the thinking/reasoning phase for models that support it (e.g., QwQ, Qwen3). When set to false, the model will skip the internal reasoning step and respond directly, which can reduce latency. Defaults to true. type: object required: - messages title: ChatCompletionRequest HTTPValidationError: title: HTTPValidationError type: object properties: detail: title: Detail type: array items: $ref: '#/components/schemas/ValidationError' ChatCompletionSystemMessageParam: type: object properties: content: oneOf: - title: Content String type: string - title: Text and Image Array type: array items: type: object properties: type: type: string enum: - text - image_url text: type: string image_url: type: string required: - type additionalProperties: false role: type: string enum: - system - user - assistant - tool required: - content - role title: ChatCompletionSystemMessageParam ChatCompletionToolParam: properties: type: type: string enum: - function function: $ref: '#/components/schemas/FunctionDefinition' type: object required: - function - type title: Function Retrieval: properties: type: type: string enum: - retrieval retrieval: $ref: '#/components/schemas/BucketIds' type: object required: - type - retrieval title: Retrieval ChatCompletionResponseFormatParam: properties: type: type: string enum: - text - json_object type: object required: - type title: ChatCompletionResponseFormatParam ValidationError: title: ValidationError required: - loc - msg - type type: object properties: loc: title: Location type: array items: anyOf: - type: string - type: integer msg: title: Message type: string type: title: Error Type type: string FunctionDefinition: properties: name: type: string description: type: string parameters: type: object additionalProperties: true type: object required: - name title: FunctionDefinition BucketIds: properties: bucket_ids: items: type: string type: array description: >- List of [embedded storage buckets](https://developers.telnyx.com/api-reference/embeddings/embed-documents) to use for retrieval-augmented generation. max_num_results: description: >- The maximum number of results to retrieve as context for the language model. type: integer type: object required: - bucket_ids title: BucketIds securitySchemes: bearerAuth: scheme: bearer type: http ````