Iimodeli namaxabiso

iimodeli ezingenasihluzo

21

ifestile yomxholo

256K

ukusuka kwi

$0.50 /1M

Iimodeli ze-open-weight ezisingathiweyo

umxholo wee-token ezingama-262,144 kwi-id nganye; i-input ne-output zibhiliwe ngokwahlukeneyo; i-id nganye yamkela oko imodeli eyilinganisayo ikwamkelayo

Imodeli	I-input	I-structured output	Ngek / cached / phuma kwe 1M	Okungakumbi
DeepSeek-V4-Pro-08133BIT-REAPDeepSeek · 1.6T MoE · 49B activeAyinasihluzo	Okubhaliweyo kungena	JSON schema	$1.95 / $0.488 / $3.90	Okungakumbi
GLM-5.23BIT-REAPZ.ai · 744B MoE · 40B activeAyinasihluzo	Okubhaliweyo kungena	JSON schema	$0.73 / $0.183 / $2.34	Okungakumbi
Kimi-K33BIT-REAPMoonshot AI · 2.8T MoE · 104B activeAyinasihluzo	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.83 / $0.958 / $19.12	Okungakumbi
Nemotron3Ultra3BIT-REAPNVIDIA · 550B hybrid Mamba-Attention MoE · 55B activeAyinasihluzo	Okubhaliweyo kungena	JSON schema	$0.75 / $0.188 / $3.30	Okungakumbi
MiniMax-M33BIT-REAPMiniMax · 428B MoE · 23B active · sparse attentionAyinasihluzo	Okubhaliweyo + umfanekiso kungena	JSON schema	$0.50 / $0.125 / $2.00	Okungakumbi
DeepSeek-V4-Flash-0731W4A16-AUTOROUND-REAPDeepSeek · 284B MoE · 13B activeAyinasihluzo	Okubhaliweyo kungena	JSON schema	$0.50 / $0.125 / $2.00	Okungakumbi
Kimi-K2.6W4A16-AUTOROUND-REAPMoonshot AI · 1T MoE · 32B activeAyinasihluzo	Okubhaliweyo + umfanekiso kungena	JSON schema	$0.78 / $0.195 / $3.67	Okungakumbi
Laguna-S-2.1W4A16-AUTOROUND-REAPPoolside · 118B MoE · 8B activeAyinasihluzo	Okubhaliweyo kungena	Akukho structured output	$0.50 / $0.125 / $2.00	Okungakumbi
inklingW4A16-AUTOROUND-REAPThinking Machines · 975B MoE · 41B activeAyinasihluzo	Okubhaliweyo + umfanekiso kungena	JSON object	$1.42 / $0.355 / $6.07	Okungakumbi
MiMo-V2.5-ProW8A16Xiaomi · 1.02T MoE · 42B active · 8-bitAyinasihluzo	Okubhaliweyo kungena	JSON schema	$0.50 / $0.125 / $2.00	Okungakumbi
MiMo-V2.5W8A16Xiaomi · 8-bit multimodal · W8A16Ayinasihluzo	Okubhaliweyo + umfanekiso kungena	JSON schema	$0.50 / $0.125 / $2.00	Okungakumbi
Hy3W8A16Tencent · 295B MoE · 21B active · 8-bitAyinasihluzo	Okubhaliweyo kungena	JSON schema	$0.50 / $0.125 / $2.00	Okungakumbi

Iimodeli zeShannon

ixabiso elinye eliqhelekileyo le-input ne-output

Imodeli	Umxholo	I-input	I-structured output	Ixabiso / 1M yee-token
Shannon 1.6 Liteshannon-1.6-liteAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.90
Shannon 1.6 Proshannon-1.6-proAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$7.80
Shannon 2 Liteshannon-2-liteAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.90
Shannon 2 Proshannon-2-proAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$5.85
Shannon 3shannon-3Ayinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.35
Shannon 3 Proshannon-3-proAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.35
Shannon 3.1shannon-3.1Ayinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.35
Shannon 3.1 Proshannon-3.1-proAyinasihluzo	192K	Okubhaliweyo + umfanekiso kungena	JSON schema	$3.35
Shannon Coder 1shannon-coder-1Ayinasihluzo	128K	Okubhaliweyo kungena	JSON schema	$8.00

Yiya kwi-Quickstart Zama Ibala lokudlala

Ukufunda umgca

Yonke imodeli iyayi-stream kwaye inokubiza ii-tool. Ezinye iimpawu ze-API zichazwe kwiphepha leCapabilities. Izakhono

Ifestile ye-context kunye nemida yokuphuma

• Ifestile ye-context ibandakanya yonke into eyifundayo imodeli kwimpendulo enye: imiyalezo yakho, uchazo lwee-tool kunye nemifanekiso.
• Intsapho yeShannon 3 ihlalutya incoko ende ngokwayo: igcina imijikelo emitsha ekwazi ukungena kwifestile kwaye iphendule.
• Kwi-stream, i-prompt ende kakhulu ibikwa njenge-error frame enohlobo invalid_request_error kunye ne-code: "context_length_exceeded".
• I-max_tokens yamkela amaxabiso ukusuka kwi-1 ukuya kwi-65,536 kuyo yonke imodeli; i-max_output_tokens kwi-GET /v1/models yeyona ncopho yoluhlu. Ixabiso elimiselweyo yi-4,096.
• Kuyo yonke imodeli, i-max_tokens yisixa esigcinwa sisicelo kwibhalansi yakho.
• Njengomda wobude bempendulo, i-max_tokens isetyenziswa ziimodeli ze-open-weight ezisingathiweyo, i-shannon-1.6-lite, i-shannon-1.6-pro kunye ne-shannon-coder-1.
• Kwiimodeli ze-open-weight ezisingathiweyo ilinganisa umbhalo wempendulo. Ukuqiqa phambi kwempendulo akubalwa kuyo, kwaye ixabiso elingaphantsi kwe-256 lisebenza njenge-256.
• I-stream ye-shannon-1.6-lite, i-shannon-1.6-pro, i-shannon-coder-1 okanye intsapho yeShannon 3 iphela nge-finish_reason: "length" xa impendulo inqunyulwe kumda wayo.

Imida nebhalansi

Ixabiso lenziwa njani

• Amaxabiso ngee-USD kwii-token ezingu-1,000,000. Ibhalansi yakho ibalwa ngee-token ezibiza i-$5.00 kwezingu-1,000,000, ngoko ixabiso lemodeli lithi zingakanani ibhalansi ezithatha ii-token zayo.
• Iimodeli zeShannon zinexabiso elinye. Ubizo luhlawulwa nge-usage.total_tokens ngelo xabiso.
• Iimodeli ze-open-weight ezisingathiweyo zinamaxabiso amathathu. Okufakwayo okufundwe kwi-cache ye-prompt kuhlawulwa ngexabiso le-cache, eliyi-25% yexabiso lokufaka lijikelezwe kwi-$0.001. Okunye okufakwayo kuhlawulwa ngexabiso lokufaka, okuphumayo ngexabiso lokuphuma.
• Iimodeli ze-open-weight ezisingathiweyo zibala ii-token nge-tokenizer yemodeli nganye. I-GET /v1/models ibonisa oku ngo-tokenizer: "original".
• I-shannon-coder-1 ibalwa ngobizo, hayi ngee-token, kwi-/v1/chat/completions nakwi-/v1/messages. Ixabiso layo elidwelisiweyo lisebenza kwi-/v1/responses.

Oko isicelo sikugcinayo, imizekelo esebenzayo yeentlawulo kunye nesabelo sobizo lweShannon Coder zikwiLimits and balance. Imida nebhalansi

Ii-id zeemodeli

Thumela enye yezi id njenge-model.

shannon-1.6-lite
shannon-1.6-pro
shannon-2-lite
shannon-2-pro
shannon-3
shannon-3-pro
shannon-3.1
shannon-3.1-pro
shannon-coder-1
DeepSeek-V4-Pro-0813-3BIT-REAP
GLM-5.2-3BIT-REAP
Kimi-K3-3BIT-REAP
Nemotron3Ultra-3BIT-REAP
MiniMax-M3-3BIT-REAP
DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP
Kimi-K2.6-W4A16-AUTOROUND-REAP
Laguna-S-2.1-W4A16-AUTOROUND-REAP
inkling-W4A16-AUTOROUND-REAP
MiMo-V2.5-Pro-W8A16
MiMo-V2.5-W8A16
Hy3-W8A16

• Oonobumba abakhulu nabancinci abubalulekanga, kwaye izithuba ezijikeleze i-id ziyasuswa: i-SHANNON-3 ne-shannon-3 yimodeli enye.
• Impendulo ihlala ithwala i-id epapashiweyo kwi-model, nokuba uyibhale njani.
• Igama lokubonisa elinjenge-Shannon 3 aliyiyo i-id.

Zamkelwa neendlela ezine ezimfutshane zokubhala.

I-id engapapashiwanga iphendulwa ngesimo 400, uhlobo invalid_request_error kunye nomyalezo unknown model: <id> kuzo zontathu ii-endpoint. Akukho yimodeli enye ephendula endaweni yayo.

{
  "error": {
    "type": "invalid_request_error",
    "message": "unknown model: gpt-4o"
  }
}

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "unknown model: gpt-4o"
  }
}

• Thumela rhoqo i-model. I-/v1/responses iphendula isicelo esingenayo nge-400. Kwi-/v1/chat/completions nakwi-/v1/messages isicelo esinjalo siphendulwa yi-shannon-1.6-lite.
• I-POST /v1/tokenize kunye ne-POST /v1/messages/count_tokens zamkela ii-id zeemodeli ze-open-weight ezisingathiweyo.

Dwelisa iimodeli

I-GET /v1/models ibuyisa iimodeli zeli phepha njenge-JSON, ngeefestile ze-context, amaxabiso kunye namandla afanayo. Yisebenzise ukuzalisa isikhethi semodeli okanye ukujonga ixabiso kwikhowudi.

GET https://api.shannon-ai.com/v1/models

from openai import OpenAI

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

for model in client.models.list():
    print(model.id)

import OpenAI from 'openai';

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

for await (const model of client.models.list()) {
  console.log(model.id);
}

curl "https://api.shannon-ai.com/v1/models"

Impendulo, imfutshanisiwe ibe yinto enye yohlobo ngalunye:

{
  "object": "list",
  "data": [
    {
      "id": "shannon-3",
      "object": "model",
      "created": 1700000000,
      "owned_by": "shannon-ai",
      "display_name": "Shannon 3",
      "context_window": 196608,
      "max_output_tokens": 65536,
      "pricing": {
        "input_per_million_usd": 3.35,
        "output_per_million_usd": 3.35,
        "currency": "USD"
      },
      "capabilities": {
        "tools": true,
        "vision": true,
        "reasoning": true,
        "reasoning_effort": false,
        "streaming": true,
        "json_schema": true
      },
      "endpoints": [
        "/v1/chat/completions",
        "/v1/messages",
        "/v1/responses"
      ]
    },
    {
      "id": "MiniMax-M3-3BIT-REAP",
      "object": "model",
      "created": 1700000000,
      "owned_by": "shannon-ai",
      "display_name": "MiniMax-M3 · 3BIT-REAP",
      "context_window": 262144,
      "max_output_tokens": 65536,
      "pricing": {
        "input_per_million_usd": 0.5,
        "cached_input_per_million_usd": 0.125,
        "output_per_million_usd": 2,
        "currency": "USD"
      },
      "tokenizer": "original",
      "capabilities": {
        "tools": true,
        "vision": true,
        "reasoning": true,
        "reasoning_effort": true,
        "streaming": true,
        "response_format": true,
        "json_schema": true,
        "prompt_caching": true
      },
      "endpoints": [
        "/v1/chat/completions",
        "/v1/messages",
        "/v1/responses",
        "/v1/messages/count_tokens",
        "/v1/tokenize"
      ]
    }
  ]
}

• I-GET /v1/models ayifuni sitshixo. Impendulo ifana kuye wonke umntu obizayo kwaye ayixhomekekanga kwiplani yakho.
• Uluhlu luqulathe ii-id ezinokubizwa. Imodeli engenakusetyenziswa okwangoku ishiyiwe kuluhlu.
• Akukho endpoint yemodeli enye: i-GET /v1/models/{id} iphendula nge-404 enohlobo not_found_error.