cURL / Python / Node.js

Alle offisielle OpenAI-biblioteker fungerer; bare base_url endres. Eksemplene bruker gpt-5.6-sol; for Astra-pakken bruk gpt-astra.

Chat Completions

curl https://gpt.teamsoclo.site/v1/chat/completions \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain closures in JavaScript"}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://gpt.teamsoclo.site/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain closures in JavaScript"},
    ],
)

print(resp.choices[0].message.content)
print(resp.usage)

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: "sk-xxx",
  baseURL: "https://gpt.teamsoclo.site/v1",
})

const resp = await client.chat.completions.create({
  model: "gpt-5.6-sol",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain closures in JavaScript" },
  ],
})

console.log(resp.choices[0].message.content)
console.log(resp.usage)

base_url må inkludere /v1 og må ikke slutte med /. Biblioteket legger til /chat/completions selv.

Svar følger OpenAI-skjemaet nøyaktig: id er chatcmpl-..., usage har prompt_tokens, completion_tokens og completion_tokens_details.reasoning_tokens. Kvoten belastes nøyaktig usage.total_tokens.

Responses API

Codex og nyere SDK-er bruker denne protokollen. Resonnerings-innstillingen bor i reasoning.effort.

curl https://gpt.teamsoclo.site/v1/responses \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "input": "Write a Python function that checks for primes",
    "reasoning": {"effort": "medium"}
  }'

resp = client.responses.create(
    model="gpt-5.6-sol",
    input="Write a Python function that checks for primes",
    reasoning={"effort": "medium"},
)
print(resp.output_text)

Resonnerings-nivå

Med Chat Completions bruk reasoning_effort (low, medium, high). Uten innstilling bruker gatewayen high. For enkle oppgaver sett low for å spare tokens:

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    reasoning_effort="low",
    messages=[{"role": "user", "content": "Translate to French: good morning"}],
)

reasoning_effort gjelder bare Chat Completions. Med Responses API bruk reasoning: {"effort": ...}; å sende reasoning_effort til /v1/responses avvises med “Unsupported parameter”.

Streaming

stream = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Write a short paragraph about autumn"}],
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.usage:
        print("\n", chunk.usage)

curl https://gpt.teamsoclo.site/v1/chat/completions \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [{"role": "user", "content": "Write a short paragraph about autumn"}],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

På vanskelige spørsmål kan modellen tenke en stund før det første token. Bruk stream: true slik at tilkoblingen ikke brytes. stream_options.include_usage gjør at det siste segmentet bærer usage slik at du kan avstemme kvoten selv.

Sende bilder (vision)

Bilder plasseres i content-arrayen, som en offentlig URL eller base64 for lokale filer.

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What error does this show?"},
            {"type": "image_url", "image_url": {"url": "https://example.com/screenshot.png"}},
        ],
    }],
)
print(resp.choices[0].message.content)

import base64

with open("screenshot.png", "rb") as f:
    b64 = base64.b64encode(f.read()).decode()

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What error does this show?"},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
        ],
    }],
)
print(resp.choices[0].message.content)

Bilder koster tokens etter størrelse. Beskjær til den relevante delen i stedet for å sende et helt 4K-skjermbilde.

Modeller og kvote via API

# Modeller denne nøkkelen kan kalle
curl https://gpt.teamsoclo.site/v1/models -H "Authorization: Bearer sk-xxx"

# Kvote (eldre OpenAI-endepunkter)
curl https://gpt.teamsoclo.site/v1/dashboard/billing/subscription -H "Authorization: Bearer sk-xxx"
curl https://gpt.teamsoclo.site/v1/dashboard/billing/usage -H "Authorization: Bearer sk-xxx"

subscription returnerer totalen i hard_limit_usd; usage returnerer det som er brukt i total_usage, i cent (divider med 100 før sammenligning). Sjekksiden gjør dette for deg.

Kom i gang

Oppsett

Support

Chat Completions

Responses API

Resonnerings-nivå

Streaming

Sende bilder (vision)

Modeller og kvote via API

​Chat Completions

​Responses API

​Resonnerings-nivå

​Streaming

​Sende bilder (vision)

​Modeller og kvote via API

Chat Completions

Responses API

Resonnerings-nivå

Streaming

Sende bilder (vision)

Modeller og kvote via API