Skip to main content
POST
/
api
/
v1
/
runtime
/
v1
/
chat
/
stream
LLM Chat Streaming
curl --request POST \
  --url https://api.runflow.ai/api/v1/runtime/v1/chat/stream \
  --header 'Content-Type: application/json' \
  --data '
{
  "projectId": "<string>",
  "model": "gpt-4",
  "messages": [
    {
      "content": "<string>",
      "tool_calls": [
        {}
      ],
      "tool_call_id": "<string>",
      "name": "<string>"
    }
  ],
  "providerName": "OpenAI Production",
  "legacy": true,
  "instructions": "<string>",
  "temperature": 0.7,
  "maxTokens": 1000,
  "topP": 0.9,
  "frequencyPenalty": 0.3,
  "presencePenalty": 0.2,
  "stop": [
    "END",
    "STOP"
  ],
  "seed": 12345,
  "tools": [
    {}
  ],
  "responseFormat": {
    "type": "json_object"
  },
  "thinking": {
    "type": "enabled",
    "budgetTokens": 5000
  },
  "serverTools": [
    {
      "type": "web_search_20250305"
    }
  ]
}
'
import requests

url = "https://api.runflow.ai/api/v1/runtime/v1/chat/stream"

payload = {
    "projectId": "<string>",
    "model": "gpt-4",
    "messages": [
        {
            "content": "<string>",
            "tool_calls": [{}],
            "tool_call_id": "<string>",
            "name": "<string>"
        }
    ],
    "providerName": "OpenAI Production",
    "legacy": True,
    "instructions": "<string>",
    "temperature": 0.7,
    "maxTokens": 1000,
    "topP": 0.9,
    "frequencyPenalty": 0.3,
    "presencePenalty": 0.2,
    "stop": ["END", "STOP"],
    "seed": 12345,
    "tools": [{}],
    "responseFormat": { "type": "json_object" },
    "thinking": {
        "type": "enabled",
        "budgetTokens": 5000
    },
    "serverTools": [{ "type": "web_search_20250305" }]
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    projectId: '<string>',
    model: 'gpt-4',
    messages: [
      {
        content: '<string>',
        tool_calls: [{}],
        tool_call_id: '<string>',
        name: '<string>'
      }
    ],
    providerName: 'OpenAI Production',
    legacy: true,
    instructions: '<string>',
    temperature: 0.7,
    maxTokens: 1000,
    topP: 0.9,
    frequencyPenalty: 0.3,
    presencePenalty: 0.2,
    stop: ['END', 'STOP'],
    seed: 12345,
    tools: [{}],
    responseFormat: {type: 'json_object'},
    thinking: {type: 'enabled', budgetTokens: 5000},
    serverTools: [{type: 'web_search_20250305'}]
  })
};

fetch('https://api.runflow.ai/api/v1/runtime/v1/chat/stream', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.runflow.ai/api/v1/runtime/v1/chat/stream",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'projectId' => '<string>',
    'model' => 'gpt-4',
    'messages' => [
        [
                'content' => '<string>',
                'tool_calls' => [
                                [
                                                                
                                ]
                ],
                'tool_call_id' => '<string>',
                'name' => '<string>'
        ]
    ],
    'providerName' => 'OpenAI Production',
    'legacy' => true,
    'instructions' => '<string>',
    'temperature' => 0.7,
    'maxTokens' => 1000,
    'topP' => 0.9,
    'frequencyPenalty' => 0.3,
    'presencePenalty' => 0.2,
    'stop' => [
        'END',
        'STOP'
    ],
    'seed' => 12345,
    'tools' => [
        [
                
        ]
    ],
    'responseFormat' => [
        'type' => 'json_object'
    ],
    'thinking' => [
        'type' => 'enabled',
        'budgetTokens' => 5000
    ],
    'serverTools' => [
        [
                'type' => 'web_search_20250305'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.runflow.ai/api/v1/runtime/v1/chat/stream"

	payload := strings.NewReader("{\n  \"projectId\": \"<string>\",\n  \"model\": \"gpt-4\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"providerName\": \"OpenAI Production\",\n  \"legacy\": true,\n  \"instructions\": \"<string>\",\n  \"temperature\": 0.7,\n  \"maxTokens\": 1000,\n  \"topP\": 0.9,\n  \"frequencyPenalty\": 0.3,\n  \"presencePenalty\": 0.2,\n  \"stop\": [\n    \"END\",\n    \"STOP\"\n  ],\n  \"seed\": 12345,\n  \"tools\": [\n    {}\n  ],\n  \"responseFormat\": {\n    \"type\": \"json_object\"\n  },\n  \"thinking\": {\n    \"type\": \"enabled\",\n    \"budgetTokens\": 5000\n  },\n  \"serverTools\": [\n    {\n      \"type\": \"web_search_20250305\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.runflow.ai/api/v1/runtime/v1/chat/stream")
  .header("Content-Type", "application/json")
  .body("{\n  \"projectId\": \"<string>\",\n  \"model\": \"gpt-4\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"providerName\": \"OpenAI Production\",\n  \"legacy\": true,\n  \"instructions\": \"<string>\",\n  \"temperature\": 0.7,\n  \"maxTokens\": 1000,\n  \"topP\": 0.9,\n  \"frequencyPenalty\": 0.3,\n  \"presencePenalty\": 0.2,\n  \"stop\": [\n    \"END\",\n    \"STOP\"\n  ],\n  \"seed\": 12345,\n  \"tools\": [\n    {}\n  ],\n  \"responseFormat\": {\n    \"type\": \"json_object\"\n  },\n  \"thinking\": {\n    \"type\": \"enabled\",\n    \"budgetTokens\": 5000\n  },\n  \"serverTools\": [\n    {\n      \"type\": \"web_search_20250305\"\n    }\n  ]\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.runflow.ai/api/v1/runtime/v1/chat/stream")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"projectId\": \"<string>\",\n  \"model\": \"gpt-4\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"providerName\": \"OpenAI Production\",\n  \"legacy\": true,\n  \"instructions\": \"<string>\",\n  \"temperature\": 0.7,\n  \"maxTokens\": 1000,\n  \"topP\": 0.9,\n  \"frequencyPenalty\": 0.3,\n  \"presencePenalty\": 0.2,\n  \"stop\": [\n    \"END\",\n    \"STOP\"\n  ],\n  \"seed\": 12345,\n  \"tools\": [\n    {}\n  ],\n  \"responseFormat\": {\n    \"type\": \"json_object\"\n  },\n  \"thinking\": {\n    \"type\": \"enabled\",\n    \"budgetTokens\": 5000\n  },\n  \"serverTools\": [\n    {\n      \"type\": \"web_search_20250305\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

Body

application/json
​
projectId
string
required

Project ID

​
provider
enum<string>
required

LLM provider

Available options:
openai,
anthropic,
bedrock,
groq,
gemini,
xai,
custom
​
model
string
required

Model name

Example:

"gpt-4"

​
messages
object[]
required

Messages

​
providerName
string

Provider name (configured in LLM Providers)

Example:

"OpenAI Production"

​
legacy
boolean

Use legacy Chat Completions API when true

Example:

true

​
instructions
string

System instructions

​
temperature
number

Temperature

Required range: 0 <= x <= 2
Example:

0.7

​
maxTokens
number

Max tokens

Example:

1000

​
topP
number

Top P (nucleus sampling)

Required range: 0 <= x <= 1
Example:

0.9

​
frequencyPenalty
number

Frequency penalty

Required range: -2 <= x <= 2
Example:

0.3

​
presencePenalty
number

Presence penalty

Required range: -2 <= x <= 2
Example:

0.2

​
stop
string[]

Stop sequences

Example:
["END", "STOP"]
​
seed
number

Seed for reproducible outputs

Example:

12345

​
tools
object[]

Tools available for the model to call

​
responseFormat
object

Response format for structured output

Example:
{ "type": "json_object" }
​
thinking
object

Enable extended thinking/reasoning for supported models

Example:
{ "type": "enabled", "budgetTokens": 5000 }
​
serverTools
string[]

Server-side tools (provider-specific). Anthropic: web_search, code_execution

Example:
[{ "type": "web_search_20250305" }]

Response

text/plain stream of chunks. Terminates when the LLM completes.