GPT Chat Completions (All Models, Full Parameters)

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum entanglement in one sentence."
    }
  ]
}
'

import requests

url = "https://direct.evolink.ai/v1/chat/completions"

payload = {
    "model": "gpt-6.1-sol",
    "messages": [
        {
            "role": "user",
            "content": "Explain quantum entanglement in one sentence."
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-6.1-sol',
    messages: [{role: 'user', content: 'Explain quantum entanglement in one sentence.'}]
  })
};

fetch('https://direct.evolink.ai/v1/chat/completions', 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://direct.evolink.ai/v1/chat/completions",
  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([
    'model' => 'gpt-6.1-sol',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Explain quantum entanglement in one sentence.'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "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://direct.evolink.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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://direct.evolink.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://direct.evolink.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}"

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

{
  "id": "chatcmpl-CvJ2p8mQxK7nR4wS",
  "object": "chat.completion",
  "created": 1786705221,
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum entanglement means the states of two particles are correlated, so measuring one instantly determines the state of the other.",
        "tool_calls": [
          {}
        ]
      },
      "logprobs": {},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 42,
    "total_tokens": 60,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 16
    }
  }
}

{
  "error": {
    "code": 400,
    "message": "Unsupported parameter: 'stop' is not supported with this model.",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/credits"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

Chat Completions API

GPT All-Model API - Chat Completions Reference

OpenAI-compatible Chat Completions API for GPT series text models; select the specific model via model (see the comparison table on the model parameter for all allowed values)
The whole series consists of reasoning models, with reasoning depth controlled by reasoning_effort; reasoning tokens are billed as output tokens
Prompt caching applies automatically: cached input tokens are billed at the lower cached rate
Supports both synchronous and streaming (SSE) modes
Supports mixed text and image input, as well as function tool calls
Server-side tools (web search, code execution, file search, MCP) are provided only on the Responses API
Note Model support varies for the sampling parameters (temperature, top_p, logprobs, and so on); see the per-parameter notes below

GPT-6: gpt-6-sol / gpt-6-luna default to medium reasoning. Function calling in Chat Completions requires an explicit reasoning_effort: "none". gpt-6-astra and gpt-6.1-sol do not support none; use the Responses API for function calling. Use Responses for GPT-6 max effort; this endpoint does not support it. gpt-6.1-terra supports none; use the Responses API for function calling with this model as well.

POST

chat

completions

GPT Chat Completions (All Models, Full Parameters)

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum entanglement in one sentence."
    }
  ]
}
'

import requests

url = "https://direct.evolink.ai/v1/chat/completions"

payload = {
    "model": "gpt-6.1-sol",
    "messages": [
        {
            "role": "user",
            "content": "Explain quantum entanglement in one sentence."
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-6.1-sol',
    messages: [{role: 'user', content: 'Explain quantum entanglement in one sentence.'}]
  })
};

fetch('https://direct.evolink.ai/v1/chat/completions', 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://direct.evolink.ai/v1/chat/completions",
  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([
    'model' => 'gpt-6.1-sol',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Explain quantum entanglement in one sentence.'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "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://direct.evolink.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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://direct.evolink.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://direct.evolink.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-6.1-sol\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Explain quantum entanglement in one sentence.\"\n    }\n  ]\n}"

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

{
  "id": "chatcmpl-CvJ2p8mQxK7nR4wS",
  "object": "chat.completion",
  "created": 1786705221,
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum entanglement means the states of two particles are correlated, so measuring one instantly determines the state of the other.",
        "tool_calls": [
          {}
        ]
      },
      "logprobs": {},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 42,
    "total_tokens": 60,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 16
    }
  }
}

{
  "error": {
    "code": 400,
    "message": "Unsupported parameter: 'stop' is not supported with this model.",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/credits"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

BaseURL: The default BaseURL is https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.

Server-side tools (web search, code execution, file search, MCP) are only available on the Responses API. The Chat Completions endpoint supports regular function tool calling only.

GPT-6: Function calling with Sol / Luna requires reasoning_effort: "none" in this endpoint. Use the Responses API for function calling with Astra, 6.1 Sol, or 6.1 Terra, or for GPT-6 max effort.

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

required

Model to call:

Model ID	Context window	Positioning
`gpt-6.1-terra`	1,050,000	Fast, efficient GPT-6.1 tier for visual reasoning, computer use, and writing
`gpt-6.1-sol`	1,050,000	Newer Sol: near-Astra performance at a lower cost (recommended)
`gpt-6-astra`	1,050,000	Flagship reasoning for demanding end-to-end work
`gpt-6-sol`	1,050,000	Complex coding and agentic workflows
`gpt-6-luna`	1,050,000	High-volume classification, extraction, and cost efficiency
`gpt-5.6-sol`	1,050,000	GPT-5.6 family, frontier reasoning
`gpt-5.6-terra`	1,050,000	GPT-5.6 family, balanced production
`gpt-5.6-luna`	1,050,000	GPT-5.6 family, high throughput and cost control
`gpt-5.5`	1,050,000	General-purpose reasoning model
`gpt-5.4`	1,050,000	General-purpose reasoning model
`gpt-5.2`	400,000	General-purpose reasoning model
`gpt-5.1`	400,000	General-purpose reasoning model

Available options:

gpt-6.1-terra,

gpt-6.1-sol,

gpt-6-astra,

gpt-6-sol,

gpt-6-luna,

gpt-5.6-sol,

gpt-5.6-terra,

gpt-5.6-luna,

gpt-5.5,

gpt-5.4,

gpt-5.2,

gpt-5.1

Example:

"gpt-6.1-sol"

messages

object[]

required

List of chat messages, supporting multi-turn context and multimodal input.

role can be system / developer / user / assistant / tool.

content can be a string or an array of content blocks. Two block types are supported: text (text) and image_url (image):

"content": [
  { "type": "text", "text": "What is in this image?" },
  {
    "type": "image_url",
    "image_url": { "url": "https://example.com/photo.png", "detail": "auto" }
  }
]

Image

Pass the public URL of the image in image_url.url
image_url can also be written directly as a string, equivalent to { "url": "..." }
detail controls image analysis fidelity: auto (default) / low / high / original
The image must be downloadable, otherwise 400 is returned

Note The block types on this API differ from those on the Responses API (which uses input_text / input_image). They cannot be mixed; using the wrong ones returns 400.

Explicit cache breakpoint for GPT-6 / GPT-5.6, placed on a content block. Up to four writes per request; an implicit breakpoint uses one slot. prompt_cache_breakpoint: {"mode": "explicit"}.

Show child attributes

Example:

[
  {
    "role": "system",
    "content": "You are a concise assistant."
  },
  {
    "role": "user",
    "content": "Explain quantum entanglement in one sentence."
  }
]

stream

boolean

default:false

Whether to return the result as a stream (an SSE event stream terminated by data: [DONE]). Defaults to false.

Example:

false

max_completion_tokens

integer

Maximum generated tokens, including reasoning. Prefer max_completion_tokens. GPT-6 accepts legacy max_tokens through conversion; if both are supplied, max_completion_tokens takes precedence and max_tokens is removed. GPT-6 Astra / Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra support up to 128,000 output tokens.

Example:

2048

reasoning_effort

enum<string>

Reasoning depth control. The allowed values vary by model:

Model	Allowed values
`gpt-6-astra` / `gpt-6.1-sol`	`low`, `medium`, `high`, `xhigh`
`gpt-6-sol` / `gpt-6-luna` / `gpt-6.1-terra`	`none`, `low`, `medium`, `high`, `xhigh`
`gpt-5.6-sol` / `gpt-5.6-terra` / `gpt-5.6-luna` / `gpt-5.5`	`none`, `low`, `medium`, `high`, `xhigh`
`gpt-5.4` / `gpt-5.2`	`none`, `low`, `medium`, `high`, `xhigh`
`gpt-5.1`	`none`, `low`, `medium`, `high`

Reasoning tokens are billed as output tokens and counted in usage.completion_tokens_details.reasoning_tokens.

GPT-6 defaults to medium. gpt-6-astra and gpt-6.1-sol do not support none; gpt-6-sol / gpt-6-luna / gpt-6.1-terra do. GPT-6 max effort is available through Responses only.

Available options:

none,

low,

medium,

high,

xhigh

Example:

"medium"

verbosity

enum<string>

How detailed the answer should be: low / medium / high.

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Rules for existing models below exclude GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra:

Note Supported by gpt-6-astra, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, and gpt-5.5; other models do not support this parameter.

Available options:

low,

medium,

high

Example:

"low"

temperature

number

Sampling temperature, ranging from 0 to 2. Lower values make the output more deterministic.

GPT-6: omit this parameter for gpt-6-astra and gpt-6.1-sol. For gpt-6-sol / gpt-6-luna / gpt-6.1-terra, adjust it only with reasoning effort set to none; omit it at other effort levels. Omitting effort selects medium, not none.

Existing models: adjust it only with reasoning effort set to none; omit it at other effort levels. gpt-5.4 / gpt-5.2 / gpt-5.1 default to none when effort is omitted, so you can adjust it directly; gpt-5.5 and the gpt-5.6 family default to medium, so set effort to none explicitly to adjust it.

Required range: 0 <= x <= 2

Example:

1

top_p

number

Nucleus sampling parameter, ranging from 0 to 1. Adjusting it together with temperature is not recommended.

Required range: 0 <= x <= 1

Example:

1

frequency_penalty

number

Frequency penalty, ranging from -2 to 2. Positive values penalize tokens by how often they have appeared, reducing repeated content.

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Rules for existing models below exclude GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra:

Note Adjustable only on gpt-5.4 / gpt-5.2 / gpt-5.1; the gpt-5.6 family and gpt-5.5 do not allow adjustment. gpt-6-astra accepts only the default value 0; passing any other value returns 400.

Required range: -2 <= x <= 2

Example:

0

presence_penalty

number

Presence penalty, ranging from -2 to 2. Positive values encourage the model to talk about new topics.

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Rules for existing models below exclude GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra:

Required range: -2 <= x <= 2

Example:

0

logprobs

boolean

default:false

Whether to return the log probabilities of each output token.

GPT-6: Astra and 6.1 Sol do not support output logprobs. For Sol / Luna and 6.1 Terra, use them only with reasoning effort none. At other levels, remove logprobs, top_logprobs, and message.output_text.logprobs from Responses include.

Rules for existing models below exclude GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra:

Note Supported only by gpt-5.4 / gpt-5.2 / gpt-5.1; the gpt-5.6 family and gpt-5.5 do not support this parameter.

GPT-6 Astra and GPT-6.1 Sol do not support this parameter.

Example:

true

top_logprobs

integer

Number of candidate tokens returned at each position, ranging from 0 to 20; must be used together with logprobs: true.

Note Same model support as logprobs.

Required range: 0 <= x <= 20

Example:

2

integer

default:1

Number of candidate replies to generate, returned as multiple entries in the choices array. All tokens (including the output of every candidate) are billed.

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Example:

1

seed

integer

Random seed. With the same seed and parameter combination, the model tries to return consistent results (best effort; full reproducibility is not guaranteed).

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Example:

42

response_format

object

Output format control:

{"type": "text"}: free-form text, the default
{"type": "json_object"}: returns valid JSON, and requires the word json to appear in messages, otherwise 400 is returned
{"type": "json_schema", "json_schema": {...}}: returns structured output following the given JSON Schema; combine it with "strict": true to enforce conformance to the schema

Show child attributes

tools

object[]

Tool list, used for function calling (client-side function calls, no per-call fee).

Server-side tools (web search, code execution, and so on) are not provided on this API; use the Responses API instead.

GPT-6: gpt-6-sol / gpt-6-luna default to medium reasoning. Function calling in Chat Completions requires an explicit reasoning_effort: "none". gpt-6-astra and gpt-6.1-sol do not support none; use the Responses API for function calling. Use Responses for GPT-6 max effort; this endpoint does not support it. gpt-6.1-terra supports none; use the Responses API for function calling with this model as well.

Show child attributes

tool_choice

Tool choice control: "auto" (default) / "none" / "required", or an object naming a specific function, such as {"type": "function", "function": {"name": "get_weather"}}.

Available options:

none,

auto,

required

parallel_tool_calls

boolean

default:true

Whether the model may call multiple tools in parallel within one turn. Defaults to true; set it to false to force calls one at a time.

GPT-6 Sol / Luna, GPT-6.1 Sol, and GPT-6.1 Terra: support for this parameter has not been confirmed; omit it from basic requests.

Example:

true

prompt_cache_key

string

Cache grouping key. GPT-6 / GPT-5.6 route cache traffic automatically; this field is not needed to optimize routing. Separate keys can distinguish cache reuse and accounting for customers or users. Keep the key stable for requests that should reuse a prefix. Earlier models can use stable keys to help cache routing.

Example:

"app-chat-v1"

user

string

End-user identifier, used to distinguish the source of calls.

Example:

"user-1024"

prompt_cache_options

object

Prompt caching options for GPT-6 and GPT-5.6. Implicit breakpoints are the default. mode: "explicit" uses only explicit breakpoints; without one, no caching occurs.

Show child attributes

Example:

{ "ttl": "30m", "mode": "implicit" }

Response

Chat completion succeeded (a JSON object; when stream=true, an SSE event stream terminated by data: [DONE])

string

Unique identifier for this conversation

Example:

"chatcmpl-CvJ2p8mQxK7nR4wS"

object

enum<string>

Response type

Available options:

chat.completion

Example:

"chat.completion"

created

integer

Creation timestamp

Example:

1786705221

model

string

Actual model name used

Example:

"gpt-6.1-sol"

choices

object[]

List of generated results (length equals n in the request)

Show child attributes

usage

object

Token usage statistics. Prompt caching applies automatically, and cached input tokens are billed at the lower cached rate.

GPT-6 bills uncached input, cache reads, cache writes, and output separately. Above 272,000 input tokens, the entire request uses 2× the regular input and cache rates and 1.5× the output rate. Built-in image generation is billed separately. See current model pricing.

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

GPT All-Model API - Chat Completions Reference

Authorizations

Body

Response