Chat Completions

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

Request diki kwazvo i-model id ne-user message imwe.

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": "Say hello in one sentence."}],
)

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: "Say hello in one sentence." }],
});

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

curl 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": "Say hello in one sentence."}]
  }'

Mhinduro i-JSON object imwe:

{
  "id": "chatcmpl-5f0c1e7a9b3d4c62a8e1f07d2b46c9a3",
  "object": "chat.completion",
  "created": 1791625200,
  "model": "shannon-3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello, it is good to meet you.",
        "reasoning_content": "The user wants a greeting in one sentence. Keep it short and friendly."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1184,
    "completion_tokens": 46,
    "total_tokens": 1230
  }
}

Headers

Request headers

Reply headers

Request fields

messages chete ndiyo inodiwa. Column ye-Applied by inotaura ma-model apo field inochinja mhinduro. Hosted open-weight models ndiwo ma-id gumi nemaviri e-model list; mhuri ye-Shannon 3 ndi-shannon-3, shannon-3-pro, shannon-3.1 ne-shannon-3.1-pro. Ma-model nemitengo

Mamwe OpenAI fields, sa-n, user, stream_options, parallel_tool_calls, presence_penalty, frequency_penalty, logit_bias, logprobs, metadata, store ne-prompt_cache_key, anogamuchirwa kuti client code iripo ishande isina kuchinjwa. Haachinji mhinduro: kunogara kuine choice imwe, uye stream inogara ichipera ine usage.

Field ine JSON type isiriyo, semuenzaniso "max_tokens": "100", inodzosa 422. Request isina messages inodaro zvakare.

Tools, structured output, reasoning ne-web search zvese zvine peji razvo: Kudanwa kwemabasa, Zvinobuda zvakarongeka, Reasoning effort, Kutsvaga pawebhu.

Request ine options

Request iyi inoisa system message, sampling fields ne-reasoning effort. Inoshandisa hosted open-weight model, inoshandisa zvese izvi.

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="DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
    messages=[
        {"role": "system", "content": "You are a physics teacher. Answer in two sentences."},
        {"role": "user", "content": "Why is the sky blue?"},
    ],
    max_tokens=512,
    temperature=0.3,
    top_p=0.9,
    seed=7,
    stop=["\n\n"],
    reasoning_effort="low",
)

message = response.choices[0].message
print(message.reasoning_content)  # the reasoning
print(message.content)            # the answer
print(response.usage)

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: "DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
  messages: [
    { role: "system", content: "You are a physics teacher. Answer in two sentences." },
    { role: "user", content: "Why is the sky blue?" },
  ],
  max_tokens: 512,
  temperature: 0.3,
  top_p: 0.9,
  seed: 7,
  stop: ["\n\n"],
  reasoning_effort: "low",
});

const message = response.choices[0].message;
console.log(message.reasoning_content); // the reasoning
console.log(message.content);           // the answer
console.log(response.usage);

curl https://api.shannon-ai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
    "messages": [
      {"role": "system", "content": "You are a physics teacher. Answer in two sentences."},
      {"role": "user", "content": "Why is the sky blue?"}
    ],
    "max_tokens": 512,
    "temperature": 0.3,
    "top_p": 0.9,
    "seed": 7,
    "stop": ["\n\n"],
    "reasoning_effort": "low"
  }'

Mhinduro ine chimiro chimwechete sepamusoro. usage yayo inowedzera zvinhu zviviri pa-hosted open-weight models: prompt tokens dzakaverengwa kubva ku-cache ne-tokens dzakashandiswa pa-reasoning.

{
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 62,
    "total_tokens": 93,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 21
    }
  }
}

Kureba kwe-output

max_tokens inoita zvinhu zviviri. Chekutanga, ndicho huwandu hwe-tokens hunochengetwa mu-balance yako request payinotanga. Mhinduro kana yapera, huwandu uhwu hunotsiviwa ne-tokens dzakashandiswa ne-request. Kana max_tokens yakakura kupfuura zvasara mu-balance yako, request inodzosa 429 Quota exceeded kunyange mhinduro pachayo ingadai yakakwana. Tumira max_tokens diki kuti uchengetedze shoma.

shannon-coder-1 inoverengwa zvakasiyana pa-endpoint iyi: request imwe neimwe i-Shannon Coder call imwe ye-plan yako, uye hapana tokens dzinochengetwa. Limits ne-balance

Chechipiri, inogumira kureba kwemhinduro pa-ma-model aya:

Pasina max_tokens kana max_completion_tokens, value i-4,096. Pa-shannon-coder-1 i-65,536.

Messages

Message imwe neimwe i-object ine role ne-content. content i-string, kana array ye-parts kana message ichitakura zvimwe kunze kwe-text.

Ne-id yemhuri ye-Shannon 3, isa mirayiro inofanira kuchengetwa mu-user message.

Pa-Shannon tiers request isina user text uye isina tools inodzosa 400 No user message provided.

Content parts

Sizes, limits nerondedzero yakazara ye-forms zvine peji razvo. Mifananidzo ne-files

Reply object

Finish reasons

Mhinduro isiri streamed inoratidza stop kana tool_calls.

Usage

Pa-hosted open-weight models, prompt_tokens ndi-messages dzako ne-tool definitions dzakaverengwa ne-tokenizer ye-model pachayo, pamwe ne-tokens dzemifananidzo chero ipi. Token counting endpoints dzinodzosa nhamba imwechete usati watumira. Kuverenga tokens

Pa-Shannon tiers, prompt_tokens inoverenga zvese zvakaverengwa ne-model kunyora mhinduro, saka yakakura kupfuura text ye-messages dzako bedzi.

Streaming

Kana stream yaiswa ku-true mhinduro inouya se-chat.completion.chunk events uye inopera ne-data: [DONE]. Chunk yekupedzisira pamberi payo inotakura finish_reason ne-usage; hapana stream_options dzinodiwa. Zvimiro ze-chunk, keep-alive lines ne-errors mukati me-stream zvine peji razvo. Kuyerera

Errors

Error i-JSON object ine error member. Ma-check anomhanya nenzira iyi: API key, request body, model id, wozoita balance. Tafura inoratidza zvinodzoserwa nguva dzakawanda ne-endpoint iyi. Rondedzero yakazara, ine zvekuedza zvakare, ine peji rayo. Zvikanganiso

{
  "error": {
    "type": "invalid_request_error",
    "message": "unknown model: no-such-model"
  }
}