Ama-model namanani

ama-model angahlungiwe

22

iwindi lomongo

256K

kusuka ku-

$0.50 /1M

Ama-model e-open-weight ahlinzekiwe

umongo wama-token angu-262,144 kuyo yonke i-id; okufakwayo nokuphumayo kubiziswa ngokwehlukana; i-id ngayinye yamukela lokho i-model eyilingisayo eyamukelayo

I-model	Okufakwayo	Okuphumayo okuhleliwe	Ingene / ecashwe / iphume ngama 1M	Okuningi
DeepSeek-V4-Pro-08133BIT-REAPDeepSeek · 1.6T MoE · 49B activeAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$1.95 / $0.488 / $3.90	Okuningi
GLM-5.23BIT-REAPZ.ai · 744B MoE · 40B activeAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$0.73 / $0.183 / $2.34	Okuningi
Kimi-K33BIT-REAPMoonshot AI · 2.8T MoE · 104B activeAkuhlungiwe	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.83 / $0.958 / $19.12	Okuningi
Nemotron3Ultra3BIT-REAPNVIDIA · 550B hybrid Mamba-Attention MoE · 55B activeAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$0.75 / $0.188 / $3.30	Okuningi
MiniMax-M33BIT-REAPMiniMax · 428B MoE · 23B active · sparse attentionAkuhlungiwe	Umbhalo + isithombe okufakwayo	I-JSON schema	$0.50 / $0.125 / $2.00	Okuningi
DeepSeek-V4-Flash-0731W4A16-AUTOROUND-REAPDeepSeek · 284B MoE · 13B activeAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$0.50 / $0.125 / $2.00	Okuningi
Kimi-K2.6W4A16-AUTOROUND-REAPMoonshot AI · 1T MoE · 32B activeAkuhlungiwe	Umbhalo + isithombe okufakwayo	I-JSON schema	$0.78 / $0.195 / $3.67	Okuningi
Laguna-S-2.1W4A16-AUTOROUND-REAPPoolside · 118B MoE · 8B activeAkuhlungiwe	Umbhalo okufakwayo	Akukho okuphumayo okuhleliwe	$0.50 / $0.125 / $2.00	Okuningi
inklingW4A16-AUTOROUND-REAPThinking Machines · 975B MoE · 41B activeAkuhlungiwe	Umbhalo + isithombe okufakwayo	Into ye-JSON	$1.42 / $0.355 / $6.07	Okuningi
MiMo-V2.5-ProW8A16Xiaomi · 1.02T MoE · 42B active · 8-bitAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$0.50 / $0.125 / $2.00	Okuningi
MiMo-V2.5W8A16Xiaomi · 8-bit multimodal · W8A16Akuhlungiwe	Umbhalo + isithombe okufakwayo	I-JSON schema	$0.50 / $0.125 / $2.00	Okuningi
Hy3W8A16Tencent · 295B MoE · 21B active · 8-bitAkuhlungiwe	Umbhalo okufakwayo	I-JSON schema	$0.50 / $0.125 / $2.00	Okuningi

Ama-model e-Shannon

izinga elilodwa lokufakwayo nokuphumayo

I-model	Umongo	Okufakwayo	Okuphumayo okuhleliwe	Intengo / ama-token ayi-1M
Shannon 1.6 Liteshannon-1.6-liteAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.90
Shannon 1.6 Proshannon-1.6-proAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$7.80
Shannon 2 Liteshannon-2-liteAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.90
Shannon 2 Proshannon-2-proAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$5.85
Shannon 3shannon-3Akuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.35
Shannon 3 Proshannon-3-proAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.35
Shannon 3.1shannon-3.1Akuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.35
Shannon 3.1 Proshannon-3.1-proAkuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.35
Shannon 3.5shannon-3.5Akuhlungiwe	192K	Umbhalo + isithombe okufakwayo	I-JSON schema	$3.35
Shannon Coder 1shannon-coder-1Akuhlungiwe	128K	Umbhalo okufakwayo	I-JSON schema	$8.00

Eya ku-Quickstart Zama i-Playground

Ukuthi umugqa ufundwa kanjani

Wonke ama-model asakaza futhi angabiza amathuluzi. Amanye amakhono e-API achazwe ekhasini le-Capabilities. Amandla

I-context window nemikhawulo yokuphumayo

• I-context window ifaka konke i-model elifundayo ukuze iphendule kanye: imilayezo yakho, izincazelo zamathuluzi nezithombe.
• Umndeni we-Shannon 3 uzivumelanisa nengxoxo ende ngokwawo: ugcina izikhathi zakamuva ezifaneleka ewindini bese uphendula.
• Ku-stream, i-prompt ende kakhulu ibikwa njenge-error frame ngohlobo invalid_request_error no-code: "context_length_exceeded".
• I-max_tokens yamukela amanani asuka ku-1 kuya ku-65,536 kuwo wonke ama-model; i-max_output_tokens ku-GET /v1/models ingumkhawulo ophezulu walolo hla. Okuvamile ngu-4,096.
• Kuwo wonke ama-model, i-max_tokens yinani isicelo esiligcina ku-balance yakho.
• Njengomkhawulo wobude bempendulo, i-max_tokens isetshenziswa ama-model e-open-weight ahlinzekiwe, i-shannon-1.6-lite, i-shannon-1.6-pro ne-shannon-coder-1.
• Ku-model e-open-weight ehlinzekiwe inqamula umbhalo wempendulo. Ukucabanga ngaphambi kwempendulo akubalwa kuyo, futhi inani elingaphansi kuka-256 lisebenza njengo-256.
• I-stream ye-shannon-1.6-lite, shannon-1.6-pro, shannon-coder-1 noma yomndeni we-Shannon 3 iphela nge-finish_reason: "length" lapho impendulo inqunyiwe emkhawulweni wayo.

Imikhawulo ne-balance

Ukuthi intengo yakhiwa kanjani

• Amanani angama-USD ngama-token angu-1,000,000. I-balance yakho ibalwa ngama-token anenani elingu-$5.00 ngama-1,000,000, ngakho intengo ye-model ithi ama-token ayo athatha i-balance engakanani.
• Ama-model e-Shannon anentengo eyodwa. Isicelo sikhokhiswa i-usage.total_tokens ngaleyo ntengo.
• Ama-model e-open-weight ahlinzekiwe anamanani amathathu. Okufakwayo okufundwa ku-prompt cache kukhokhiswa ngentengo ye-cache, engu-25% yentengo yokufakwayo egoqelwe ku-$0.001. Okunye okufakwayo kukhokhiswa ngentengo yokufakwayo, okuphumayo ngentengo yokuphumayo.
• Ama-model e-open-weight ahlinzekiwe abala ama-token nge-tokenizer ye-model ngayinye. I-GET /v1/models ikuphawula lokhu ngo-tokenizer: "original".
• I-shannon-coder-1 ibalwa ngezicelo, hhayi ngama-token, ku-/v1/chat/completions na-/v1/messages. Intengo yayo ebhalwe isebenza ku-/v1/responses.

Okugcinwa yisicelo, izibonelo ezisebenzayo zokukhokha ne-allowance yezicelo ze-Shannon Coder kusekhasini le-Limits and balance. Imikhawulo ne-balance

Ama-id ama-model

Thumela eyodwa yalawa ma-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-3.5
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

• Ukuthi onkulu noma amancane akunandaba, futhi izikhala eduze kwe-id ziyasuswa: i-SHANNON-3 ne-shannon-3 yi-model efanayo.
• Impendulo ihlala iphethe i-id eshicilelwe ku-model, noma ngabe uthumele ukubhala kwayiphi.
• Igama lokubonisa elinjenge-Shannon 3 aliyona i-id.

Kuyamukelwa futhi ukubhala okune okufushane.

I-id engashicilelwe iphendulwa ngesimo 400, uhlobo invalid_request_error nomlayezo unknown model: <id> kuwo wonke ama-endpoint amathathu. Ayikho enye i-model ephendula esikhundleni sayo.

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

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

• Thumela njalo i-model. I-/v1/responses iphendula isicelo esingenayo nge-400. Ku-/v1/chat/completions na-/v1/messages isicelo esinjalo siphendulwa yi-shannon-1.6-lite.
• I-POST /v1/tokenize ne-POST /v1/messages/count_tokens zamukela ama-id ama-model e-open-weight ahlinzekiwe.

Uhlu lwama-model

I-GET /v1/models ibuyisa ama-model alelikhasi njenge-JSON, ngama-context window, amanani namakhono afanayo. Yisebenzise ukugcwalisa i-model picker noma ukuhlola intengo ekhodini.

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, ifinyeziwe ibe yinto eyodwa 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 ayidingi key. Impendulo ifana kubo bonke ababizayo futhi ayincikile kuhlelo lwakho.
• Uhlu luphethe ama-id angabizwa. I-model engakwazi ukusetshenziswa njengamanje ishiywa ngaphandle kwalo.
• Ayikho i-endpoint ye-model eyodwa: i-GET /v1/models/{id} iphendula nge-404 ngohlobo not_found_error.