Kutanga nekukurumidza

Itai request yekutanga: tora key yako, tumira message imwe uye uverenge mhinduro. API inotaura OpenAI ne-Anthropic formats, saka SDK yauri kushandisa kare inoshanda mushure mekuchinja base URL ne-key yayo.

1. Tora key yako

Account imwe neimwe ine API key imwe. Pinda, vhura Keys & usage uye uikope. Key inoshanda pa-endpoint imwe neimwe nema-model ese. Keys & usage

2. Taridzira client yako ku-API

Ma-endpoint ese ari pasi pe-base URL imwe. OpenAI SDK inoitora ine /v1 kumagumo; Anthropic SDK inoitora isina, nekuti pachayo inowedzera /v1/messages.

Client	Base URL
OpenAI SDKs ne-OpenAI-compatible clients	`https://api.shannon-ai.com/v1`
Anthropic SDKs	`https://api.shannon-ai.com`

Ma-endpoint matatu anogadzira text. Anosvika kuma-model akafanana; sarudza iro rine format yatoshandiswa ne-code yako.

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

3. Tumira request yekutanga

Tumira user message imwe ku-shannon-3 pa-Chat Completions endpoint. Tsiva YOUR_API_KEY ne-key yako.

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	Mhando	Default	Tsananguro
`model`	`string`		Id ye-model inopindura. Ma-id akanyorwa pa-Models & pricing.
`messages`	`array`		Hurukuro kusvika zvino: objects dzine `role` ne-`content`. `user` message yekupedzisira ndiyo prompt. Inodiwa.
`max_tokens`	`integer`	`4096`	Output budget ye-request, kubva ku-1 kusvika ku-65,536. Request inochengeta huwandu uhwu kubva mu-balance yako uye inobhadharwa zvayakashandisa chaizvo.
`stream`	`boolean`	`false`	`true` inotumira mhinduro chimedu nechimedu ichiri kunyorwa.

Request body i-JSON uye inoda header Content-Type: application/json. Rondedzero yakazara ye-fields iri papeji re-endpoint. Chat Completions

Mhinduro

Call isina stream inodzosa JSON object imwe kana mhinduro yapera. Ma-text nenhamba dziri pazasi i-mienzaniso.

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	Mhando	Tsananguro
`id`	`string`	`chatcmpl-` inoteverwa ne-hexadecimal characters 32.
`object`	`string`	Inogara iri `chat.completion`.
`created`	`integer`	Nguva yemhinduro mumasekonzi e-Unix.
`model`	`string`	Published id ye-model yakapindura, kunyange kana wakatumira alias kana manyorerwo mamwe.
`choices`	`array`	Inogara iri entry imwe, ine `index` 0.
`choices[0].message.role`	`string`	Inogara iri `assistant`.
`choices[0].message.content`	`string \| null`	Mhinduro. Inogona kuva `null` kana mhinduro ichitakura `tool_calls`.
`choices[0].message.reasoning_content`	`string \| null`	Reasoning ye-model pamberi pemhinduro yayo, kana `null` kana isipo.
`choices[0].message.tool_calls`	`array`	Iripo chete kana model ichidanidzira imwe ye-tools dzawakaratidza.
`choices[0].finish_reason`	`string`	`stop` yemhinduro, `tool_calls` kana model ichidanidzira tool.
`usage.prompt_tokens`	`integer`	Tokens dzakaverengwa ne-model pamhinduro iyi. Pa-`shannon-2-*` nemhuri ye-Shannon 3 izvi zvinogona kuva zvakawanda kupfuura text yawatumira.
`usage.completion_tokens`	`integer`	Tokens dzakanyorwa ne-model.
`usage.total_tokens`	`integer`	Huwandu hwese. Mutengo we-Shannon model unoverengwa kubva panhamba iyi.

usage ine huwandu hwe-tokens, kwete mari. Zvakatorwa ne-call kubva mu-balance yako zvinoratidzwa pa-request imwe neimwe pa-Keys & usage; kuti zvinoverengwa sei kuri pa-Limits ne-balance. Limits ne-balance
Mhinduro imwe neimwe, kunyange error ne-stream, ine header x-request-id. Kana request yako ichitakura x-request-id header, value yayo inodzoka; kana kwete value i-hexadecimal characters 12. Ichengete mu-logs dzako: inotumidza request iyi imwe chete.

Call imwechete se-stream

Isa stream ku-true kuverenga mhinduro ichiri kunyorwa. Zvimwe zvese mu-request zvinoramba zvakadaro.

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 imwe neimwe ye-stream i-mutsara mumwe unotanga ne-data: uye une JSON object. Frame imwe, yakaprintwa pamitsara yakawanda:

Frame imwe

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

Frames, nenhevedzano	delta	finish_reason
Apo model ichifunga. Zero kana ma-frame akawanda.	`{"reasoning_content": "…"}`	`null`
Mhinduro, chimedu nechimedu. Zero kana ma-frame akawanda.	`{"content": "…"}`	`null`
JSON frame yekupedzisira. Inotakurawo `usage`; hauna kufanira kuikumbira.	`{}`	`"stop"`
Kupera kwe-stream: mutsara `data: [DONE]`.

Mhinduro ine status 200 ne-content-type: text/event-stream. Frame imwe neimwe i-mutsara data: <json> unoteverwa nemutsara usina chinhu.
Mutsara : ping unouya masekonzi 15 ega ega. Comment inochengeta connection yakavhurika; SSE clients dzinoisiya.
Kundikana mushure mekuti stream yavhurwa kunouya se-frame data: {"error": {…}}. Status inoramba iri 200, saka tarisa ma-frame.

Kuyerera

Kana call ikakundikana

Error i-JSON object ine error ine type ne-message. Idzi ndidzo mhinduro dzinosangana nadzo call yekutanga nguva dzakawanda.

Status	Mhando	Message	Zvinorehwa
`401`	`authentication_error`	`Missing authentication`	Hapana key yakasvika ku-API. Tumira `Authorization: Bearer` inoteverwa ne-key yako.
`401`	`authentication_error`	`Invalid API key`	Key haisi key yazvino ye-account. Ikopere zvakare kubva ku-Keys & usage.
`400`	`invalid_request_error`	`unknown model: <id>`	`model` haisi published id. Shandisa id kubva ku-Models & pricing.
`422`	`invalid_request_error`	`Failed to deserialize the JSON body into the target type…`	Field ine JSON type isiriyo, kana `messages` haisipo.
`429`	`rate_limit_error`	`Quota exceeded. Upgrade your plan at shannon-ai.com/plan`	Output budget ye-request haikwani mu-balance yako.

Zvikanganiso

Kwekuenda zvinotevera

Ma-model nemitengo — Sarudza model: ids, context windows nemitengo.
Chat Completions — Request field imwe neimwe, reply field ne-stream event ye-endpoint yawadanidzira.
Kuyerera — Ma-frame e-stream, keep-alive lines ne-errors mukati me-stream.
Kudanwa kwemabasa — Siya model ichidanidzira functions dzako.
Limits ne-balance — Zvinochengetwa ne-request nemutengo wayo, uye ma-request mangani aungatumira.
API Playground — Edza ma-request mu-browser ne-key yako.