Send Chat Completion Request with OpenRouter API

Pipedream makes it easy to connect APIs for OpenRouter and 2,500+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

Next, do this

Send Chat Completion Request with the OpenRouter API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

Create a workflow to Send Chat Completion Request with the OpenRouter API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Configure the Send Chat Completion Request action
1. Connect your OpenRouter account
2. Select a Model
3. Configure Messages
4. Optional- Configure Max Tokens
5. Optional- Configure Temperature
6. Optional- Configure Seed
7. Optional- Configure Top P
8. Optional- Configure Top K
9. Optional- Configure Frequency Penalty
10. Optional- Configure Presence Penalty
11. Optional- Configure Repetition Penalty
12. Optional- Configure Logit Bias
13. Optional- Configure Top Logprobs
14. Optional- Configure Min P
15. Optional- Configure Top A
16. Optional- Configure Transforms
17. Select one or more Models
18. Optional- Configure Sort
19. Optional- Select a Reasoning Effort
20. Optional- Configure Reasoning Max Tokens
21. Optional- Configure Reasoning Exclude
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

Send Chat Completion Request with OpenRouter API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + OpenRouter

Try it

Send Chat Completion Request with OpenRouter API on New Submission from Typeform API

Typeform + OpenRouter

Try it

Send Chat Completion Request with OpenRouter API on New Submission (Instant) from Jotform API

Jotform + OpenRouter

Try it

Send Chat Completion Request with OpenRouter API on New Scheduled Tasks from Pipedream API

Pipedream + OpenRouter

Try it

Send Chat Completion Request with OpenRouter API on New Download Counts from npm API

npm + OpenRouter

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Send Chat Completion Request on OpenRouter

Description:Send a chat completion request to a selected model. [See the documentation](https://openrouter.ai/docs/api-reference/chat-completion)

Version:0.0.1

Key:openrouter-send-chat-completion-request

View on GitHub

Code#

import { ConfigurationError } from "@pipedream/platform";
import { parseObject } from "../../common/utils.mjs";
import openrouter from "../../openrouter.app.mjs";

export default {
  key: "openrouter-send-chat-completion-request",
  name: "Send Chat Completion Request",
  version: "0.0.1",
  description: "Send a chat completion request to a selected model. [See the documentation](https://openrouter.ai/docs/api-reference/chat-completion)",
  type: "action",
  props: {
    openrouter,
    model: {
      propDefinition: [
        openrouter,
        "model",
      ],
    },
    messages: {
      type: "string[]",
      label: "Messages",
      description: "A list of objects containing role and content. E.g. **{\"role\":\"user\", \"content\":\"text\"}**. [See the documentation](https://openrouter.ai/docs/api-reference/chat-completion#request.body.messages) for further details.",
    },
    maxTokens: {
      propDefinition: [
        openrouter,
        "maxTokens",
      ],
    },
    temperature: {
      propDefinition: [
        openrouter,
        "temperature",
      ],
    },
    seed: {
      propDefinition: [
        openrouter,
        "seed",
      ],
    },
    topP: {
      propDefinition: [
        openrouter,
        "topP",
      ],
    },
    topK: {
      propDefinition: [
        openrouter,
        "topK",
      ],
    },
    frequencyPenalty: {
      propDefinition: [
        openrouter,
        "frequencyPenalty",
      ],
    },
    presencePenalty: {
      propDefinition: [
        openrouter,
        "presencePenalty",
      ],
    },
    repetitionPenalty: {
      propDefinition: [
        openrouter,
        "repetitionPenalty",
      ],
    },
    logitBias: {
      propDefinition: [
        openrouter,
        "logitBias",
      ],
    },
    togLogprobs: {
      propDefinition: [
        openrouter,
        "togLogprobs",
      ],
    },
    minP: {
      propDefinition: [
        openrouter,
        "minP",
      ],
    },
    topA: {
      propDefinition: [
        openrouter,
        "topA",
      ],
    },
    transforms: {
      propDefinition: [
        openrouter,
        "transforms",
      ],
    },
    models: {
      propDefinition: [
        openrouter,
        "model",
      ],
      type: "string[]",
      label: "Models",
      description: "Alternate list of models for routing overrides.",
    },
    sort: {
      propDefinition: [
        openrouter,
        "sort",
      ],
    },
    effort: {
      propDefinition: [
        openrouter,
        "effort",
      ],
    },
    reasoningMaxTokens: {
      propDefinition: [
        openrouter,
        "reasoningMaxTokens",
      ],
    },
    exclude: {
      propDefinition: [
        openrouter,
        "exclude",
      ],
    },
  },
  async run({ $ }) {
    if (this.effort && this.reasoningMaxTokens) {
      throw new ConfigurationError("**Reasoning Effort** and **Reasoning Max Tokens** cannot be used simultaneously.");
    }
    const data = {
      model: this.model,
      messages: parseObject(this.messages),
      stream: false,
      maxTokens: this.maxTokens,
      temperature: this.temperature && parseFloat(this.temperature),
      seed: this.seed,
      topP: this.topP && parseFloat(this.topP),
      topK: this.topK,
      frequencyPenalty: this.frequencyPenalty && parseFloat(this.frequencyPenalty),
      presencePenalty: this.presencePenalty && parseFloat(this.presencePenalty),
      repetitionPenalty: this.repetitionPenalty && parseFloat(this.repetitionPenalty),
      logitBias: this.logitBias,
      togLogprobs: this.togLogprobs,
      minP: this.minP && parseFloat(this.minP),
      topA: this.topA && parseFloat(this.topA),
      transforms: this.transforms,
      models: this.models,
    };
    if (this.sort) {
      data.provider = {
        sort: this.sort,
      };
    }
    const reasoning = {};
    if (this.effort) {
      reasoning.effort =  this.effort;
    }
    if (this.reasoningMaxTokens) {
      reasoning.max_tokens = parseFloat(this.reasoningMaxTokens);
    }
    if (this.exclude) {
      reasoning.exclude =  this.exclude;
    }
    if (Object.entries(reasoning).length) {
      data.reasoning = reasoning;
    }
    const response = await this.openrouter.sendChatCompetionRequest({
      $,
      data,
      timeout: 1000 * 60 * 5,
    });
    if (response.error) {
      throw new ConfigurationError(response.error.message);
    }
    $.export("$summary", `A new chat completion request with Id: ${response.id} was successfully created!`);
    return response;
  },
};

Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
OpenRouter	`openrouter`	`app`	This component uses the OpenRouter app.
Model	`model`	`string`	Select a value from the drop down menu.
Messages	`messages`	`string[]`	A list of objects containing role and content. E.g. {"role":"user", "content":"text"}. See the documentation for further details.
Max Tokens	`maxTokens`	`integer`	Maximum number of tokens. (range: [1, context_length)).
Temperature	`temperature`	`string`	Sampling temperature. (range: [0, 2]).
Seed	`seed`	`integer`	Seed for deterministic outputs.
Top P	`topP`	`string`	Top-p sampling value. (range: (0, 1]).
Top K	`topK`	`integer`	Top-k sampling value. (range: [1, Infinity)).
Frequency Penalty	`frequencyPenalty`	`string`	Frequency penalty. (range: [-2, 2]).
Presence Penalty	`presencePenalty`	`string`	Presence penalty. (range: [-2, 2]).
Repetition Penalty	`repetitionPenalty`	`string`	Repetition penalty. (range: (0, 2]).
Logit Bias	`logitBias`	`string[]`	A list of token IDs to bias values.
Top Logprobs	`togLogprobs`	`integer`	Number of top log probabilities to return.
Min P	`minP`	`string`	Minimum probability threshold. (range: [0, 1]).
Top A	`topA`	`integer`	Alternate top sampling parameter. (range: [0, 1]).
Transforms	`transforms`	`string[]`	List of prompt transforms (OpenRouter-only).
Models	`models`	`string[]`	Select a value from the drop down menu.
Sort	`sort`	`string`	Sort preference (e.g., price, throughput).
Reasoning Effort	`effort`	`string`	Select a value from the drop down menu:`highmediumlow`
Reasoning Max Tokens	`reasoningMaxTokens`	`string`	Non-OpenAI-style reasoning effort setting. Cannot be used simultaneously with effort.
Reasoning Exclude	`exclude`	`boolean`	Whether to exclude reasoning from the response