Kuyamba mwachangu

Tumizani pempho loyamba: pezani kiyi yanu, tumizani message imodzi ndi kuwerenga yankho. API imalankhula mitundu ya OpenAI ndi Anthropic, choncho SDK yomwe mukugwiritsa ntchito kale imagwira ntchito mukasintha base URL ndi kiyi yake.

1. Pezani kiyi yanu

Akaunti iliyonse ili ndi API key imodzi. Lowani, tsegulani Keys & usage ndi kuikopera. Kiyi imagwira ntchito pa endpoint iliyonse ndi model iliyonse. Keys & usage

2. Lozani client yanu ku API

Ma endpoint onse ali pansi pa base URL imodzi. OpenAI SDK imailandira ndi /v1 kumapeto; Anthropic SDK imailandira popanda, chifukwa imawonjezera /v1/messages yokha.

Client	Base URL
OpenAI SDK ndi ma client ogwirizana ndi OpenAI	`https://api.shannon-ai.com/v1`
Anthropic SDK	`https://api.shannon-ai.com`

Ma endpoint atatu amapanga text. Amafika ku ma model omwewo; sankhani yomwe mtundu wake code yanu imagwiritsa ntchito kale.

Endpoint	Mtundu
`POST /v1/chat/completions`	OpenAI Chat Completions
`POST /v1/messages`	Anthropic Messages
`POST /v1/responses`	OpenAI Responses

3. Tumizani pempho loyamba

Tumizani message imodzi ya user ku shannon-3 pa endpoint ya Chat Completions. Sinthani YOUR_API_KEY ndi kiyi yanu.

POST https://api.shannon-ai.com/v1/chat/completions

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

response = client.chat.completions.create(
    model="shannon-3",
    messages=[
        {"role": "user", "content": "Hello, Shannon!"}
    ],
    max_tokens=1024
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

const response = await client.chat.completions.create({
  model: 'shannon-3',
  messages: [
    { role: 'user', content: 'Hello, Shannon!' }
  ],
  max_tokens: 1024
});

console.log(response.choices[0].message.content);

package main

import (
    "context"
    "fmt"
    openai "github.com/sashabaranov/go-openai"
)

func main() {
    config := openai.DefaultConfig("YOUR_API_KEY")
    config.BaseURL = "https://api.shannon-ai.com/v1"
    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "shannon-3",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Hello, Shannon!"},
            },
            MaxTokens: 1024,
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

curl -X POST "https://api.shannon-ai.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "messages": [
      {"role": "user", "content": "Hello, Shannon!"}
    ],
    "max_tokens": 1024
  }'

Field	Mtundu	Yokhazikika	Kufotokozera
`model`	`string`		Id ya model yomwe imayankha. Ma id alembedwa pa Models & pricing.
`messages`	`array`		Zokambirana mpaka pano: ma object okhala ndi `role` ndi `content`. Message yomaliza ya `user` ndi prompt. Yofunika.
`max_tokens`	`integer`	`4096`	Output budget ya pempho, kuyambira 1 mpaka 65,536. Pempho limasunga kuchuluka kumeneku pa balance yanu ndipo limaperekedwa mtengo wa zomwe lagwiritsa ntchito kwenikweni.
`stream`	`boolean`	`false`	`true` imatumiza yankho chigawo ndi chigawo pamene likulembedwa.

Body ya pempho ndi JSON ndipo imafuna header Content-Type: application/json. Mndandanda wonse wa ma field uli patsamba la endpoint. Chat Completions

Yankho

Call yopanda stream imabweza JSON object imodzi yankho likatha. Ma text ndi manambala omwe ali pansipa ndi zitsanzo.

200 JSON

{
  "id": "chatcmpl-9b2f6c1e4a7d4f0f8a3c5d2e1b6a7c90",
  "object": "chat.completion",
  "created": 1791590400,
  "model": "shannon-3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! What would you like to work on?",
        "reasoning_content": "A greeting. A short, friendly reply fits."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1386,
    "completion_tokens": 74,
    "total_tokens": 1460
  }
}

Field	Mtundu	Kufotokozera
`id`	`string`	`chatcmpl-` yotsatiridwa ndi zilembo 32 za hexadecimal.
`object`	`string`	Nthawi zonse `chat.completion`.
`created`	`integer`	Nthawi ya yankho mu masekondi a Unix.
`model`	`string`	Id yofalitsidwa ya model yomwe yayankha, ngakhale mutatumiza alias kapena kalembedwe kena.
`choices`	`array`	Nthawi zonse entry imodzi, ndi `index` 0.
`choices[0].message.role`	`string`	Nthawi zonse `assistant`.
`choices[0].message.content`	`string \| null`	Yankho. Likhoza kukhala `null` pamene yankho lili ndi `tool_calls`.
`choices[0].message.reasoning_content`	`string \| null`	Reasoning ya model isanayankhe, kapena `null` ngati palibe.
`choices[0].message.tool_calls`	`array`	Imakhalapo pokhapokha model ikayitana imodzi mwa ma tool omwe mwalengeza.
`choices[0].finish_reason`	`string`	`stop` pa yankho, `tool_calls` pamene model iyitana tool.
`usage.prompt_tokens`	`integer`	Ma token omwe model yawerenga pa yankho ili. Pa `shannon-2-*` ndi banja la Shannon 3 izi zikhoza kukhala zoposa text yomwe mwatumiza.
`usage.completion_tokens`	`integer`	Ma token omwe model yalemba.
`usage.total_tokens`	`integer`	Chiwerengero chonse. Mtengo wa model ya Shannon umawerengedwa kuchokera ku nambala iyi.

usage ili ndi chiwerengero cha ma token, osati ndalama. Zomwe call yatenga pa balance yanu zimaonetsedwa pa pempho lililonse pa Keys & usage; momwe zimawerengedwera zili pa Malire ndi balance. Malire ndi balance
Yankho lililonse, ngakhale cholakwika ndi stream, lili ndi header ya x-request-id. Ngati pempho lanu lili ndi header ya x-request-id, mtengo wake umabwerera; apo ayi mtengo ndi zilembo 12 za hexadecimal. Usungeni mu ma log anu: umatchula pempho limodzi limeneli.

Call yomweyo ngati stream

Khazikitsani stream kukhala true kuti muwerenge yankho pamene likulembedwa. Zina zonse mu pempho zimakhala chimodzimodzi.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

stream = client.chat.completions.create(
    model="shannon-3",
    messages=[
        {"role": "user", "content": "Hello, Shannon!"}
    ],
    max_tokens=1024,
    stream=True
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

const stream = await client.chat.completions.create({
  model: 'shannon-3',
  messages: [
    { role: 'user', content: 'Hello, Shannon!' }
  ],
  max_tokens: 1024,
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

curl -N -X POST "https://api.shannon-ai.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "messages": [
      {"role": "user", "content": "Hello, Shannon!"}
    ],
    "max_tokens": 1024,
    "stream": true
  }'

Frame iliyonse ya stream ndi mzere umodzi woyambira ndi data: wokhala ndi JSON object. Frame imodzi, yosindikizidwa pa mizere ingapo:

Frame imodzi

{
  "id": "chatcmpl-9b2f6c1e4a7d4f0f8a3c5d2e1b6a7c90",
  "object": "chat.completion.chunk",
  "created": 1791590400,
  "model": "shannon-3",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "Hello! "
      },
      "finish_reason": null
    }
  ]
}

Ma frame, motsatira	delta	finish_reason
Pamene model ikuganiza. Frame zero kapena zingapo.	`{"reasoning_content": "…"}`	`null`
Yankho, chigawo ndi chigawo. Frame zero kapena zingapo.	`{"content": "…"}`	`null`
Frame yomaliza ya JSON. Imanyamulanso `usage`; simuyenera kuipempha.	`{}`	`"stop"`
Mapeto a stream: mzere `data: [DONE]`.

Yankho lili ndi status 200 ndi content-type: text/event-stream. Frame iliyonse ndi mzere data: <json> wotsatiridwa ndi mzere wopanda kanthu.
Mzere : ping umafika masekondi 15 aliwonse. Ndi comment yosunga connection yotsegula; ma SSE client amaudumpha.
Cholakwika chomwe chachitika stream itatsegulidwa chimafika ngati frame data: {"error": {…}}. Status imakhalabe 200, choncho yang'anani ma frame.

Kutsitsa nthawi yeniyeni

Call ikalephera

Cholakwika ndi JSON object yokhala ndi error yomwe ili ndi type ndi message. Awa ndi mayankho omwe call yoyamba imakumana nawo kawirikawiri.

Status	Mtundu	Message	Tanthauzo lake
`401`	`authentication_error`	`Missing authentication`	Palibe kiyi yomwe yafika ku API. Tumizani `Authorization: Bearer` yotsatiridwa ndi kiyi yanu.
`401`	`authentication_error`	`Invalid API key`	Kiyi si kiyi yamakono ya akaunti. Koperaninso kuchokera ku Keys & usage.
`400`	`invalid_request_error`	`unknown model: <id>`	`model` si id yofalitsidwa. Gwiritsani id yochokera ku Models & pricing.
`422`	`invalid_request_error`	`Failed to deserialize the JSON body into the target type…`	Field ili ndi JSON type yolakwika, kapena `messages` ikusowa.
`429`	`rate_limit_error`	`Quota exceeded. Upgrade your plan at shannon-ai.com/plan`	Output budget ya pempho siikwana mu balance yanu.

Zolakwika

Kopitirira kuti

Ma model ndi mitengo — Sankhani model: ma id, context window ndi mitengo.
Chat Completions — Field iliyonse ya pempho, field ya yankho ndi stream event ya endpoint yomwe mwaitana.
Kutsitsa nthawi yeniyeni — Ma frame a stream, mizere ya keep-alive ndi zolakwika mkati mwa stream.
Kuyitana mafunkseni — Lolani model kuyitana ma function anu.
Malire ndi balance — Zomwe pempho limasunga ndi kuwononga, ndi ma pempho angati omwe mungatumize.
API Playground — Yesani ma pempho mu browser ndi kiyi yanu.