Li-model le litheko

li-model tse se nang censorship

22

fensetere ea context

256K

ho tloha

$0.50 /1M

Li-model tse hosted tsa open-weight

context ea tokens tse 262,144 ho id e 'ngoe le e 'ngoe; input le output li ntšetsoa chelete ka thoko; id e 'ngoe le e 'ngoe e amohela se amohelang model eo e e etselitsoeng

Model	Input	Structured output	In / cached / out ka 1M	Tse ling
DeepSeek-V4-Pro-08133BIT-REAPDeepSeek · 1.6T MoE · 49B activeHa e na censorship	Mongolo ho kena	JSON schema	$1.95 / $0.488 / $3.90	Tse ling
GLM-5.23BIT-REAPZ.ai · 744B MoE · 40B activeHa e na censorship	Mongolo ho kena	JSON schema	$0.73 / $0.183 / $2.34	Tse ling
Kimi-K33BIT-REAPMoonshot AI · 2.8T MoE · 104B activeHa e na censorship	Mongolo + setšoantšo ho kena	JSON schema	$3.83 / $0.958 / $19.12	Tse ling
Nemotron3Ultra3BIT-REAPNVIDIA · 550B hybrid Mamba-Attention MoE · 55B activeHa e na censorship	Mongolo ho kena	JSON schema	$0.75 / $0.188 / $3.30	Tse ling
MiniMax-M33BIT-REAPMiniMax · 428B MoE · 23B active · sparse attentionHa e na censorship	Mongolo + setšoantšo ho kena	JSON schema	$0.50 / $0.125 / $2.00	Tse ling
DeepSeek-V4-Flash-0731W4A16-AUTOROUND-REAPDeepSeek · 284B MoE · 13B activeHa e na censorship	Mongolo ho kena	JSON schema	$0.50 / $0.125 / $2.00	Tse ling
Kimi-K2.6W4A16-AUTOROUND-REAPMoonshot AI · 1T MoE · 32B activeHa e na censorship	Mongolo + setšoantšo ho kena	JSON schema	$0.78 / $0.195 / $3.67	Tse ling
Laguna-S-2.1W4A16-AUTOROUND-REAPPoolside · 118B MoE · 8B activeHa e na censorship	Mongolo ho kena	Ha ho structured output	$0.50 / $0.125 / $2.00	Tse ling
inklingW4A16-AUTOROUND-REAPThinking Machines · 975B MoE · 41B activeHa e na censorship	Mongolo + setšoantšo ho kena	Ntho ea JSON	$1.42 / $0.355 / $6.07	Tse ling
MiMo-V2.5-ProW8A16Xiaomi · 1.02T MoE · 42B active · 8-bitHa e na censorship	Mongolo ho kena	JSON schema	$0.50 / $0.125 / $2.00	Tse ling
MiMo-V2.5W8A16Xiaomi · 8-bit multimodal · W8A16Ha e na censorship	Mongolo + setšoantšo ho kena	JSON schema	$0.50 / $0.125 / $2.00	Tse ling
Hy3W8A16Tencent · 295B MoE · 21B active · 8-bitHa e na censorship	Mongolo ho kena	JSON schema	$0.50 / $0.125 / $2.00	Tse ling

Li-model tsa Shannon

theko e le 'ngoe e sa fetoheng bakeng sa input le output

Model	Context	Input	Structured output	Theko / 1M tokens
Shannon 1.6 Liteshannon-1.6-liteHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.90
Shannon 1.6 Proshannon-1.6-proHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$7.80
Shannon 2 Liteshannon-2-liteHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.90
Shannon 2 Proshannon-2-proHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$5.85
Shannon 3shannon-3Ha e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.35
Shannon 3 Proshannon-3-proHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.35
Shannon 3.1shannon-3.1Ha e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.35
Shannon 3.1 Proshannon-3.1-proHa e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.35
Shannon 3.5shannon-3.5Ha e na censorship	192K	Mongolo + setšoantšo ho kena	JSON schema	$3.35
Shannon Coder 1shannon-coder-1Ha e na censorship	128K	Mongolo ho kena	JSON schema	$8.00

Eya ho Quickstart Leka Playground

Mokhoa oa ho bala mola

Model e 'ngoe le e 'ngoe e etsa streaming mme e ka bitsa lisebelisoa. Likarolo tse ling tsa API li hlalositsoe leqepheng la Capabilities. Bokgoni

Context window le meeli ea output

• Context window e koahela tsohle tseo model e li balang bakeng sa karabo e le 'ngoe: melaetsa ea hau, litlhaloso tsa tool le litšoantšo.
• Lelapa la Shannon 3 le lekanya moqoqo o molelele ka bolona: le boloka li-turn tse ncha tse kenang fensetereng mme la araba.
• Ho stream, prompt e telele haholo e tlalehoa e le frame ea phoso e nang le mofuta invalid_request_error le code: "context_length_exceeded".
• max_tokens e amohela litekanyo ho tloha ho 1 ho isa ho 65,536 ho model e 'ngoe le e 'ngoe; max_output_tokens ho GET /v1/models ke sehlohlolo sa sebaka seo. Default ke 4,096.
• Ho model e 'ngoe le e 'ngoe, max_tokens ke palo eo kopo e e behelang thoko ho balance ea hau.
• E le moeli oa bolelele ba karabo, max_tokens e sebelisoa ke li-model tse hosted tsa open-weight, shannon-1.6-lite, shannon-1.6-pro le shannon-coder-1.
• Ho li-model tse hosted tsa open-weight e lekanyetsa mongolo oa karabo. Reasoning pele ho karabo ha e baloe ho eona, mme boleng bo ka tlase ho 256 bo sebetsa e le 256.
• Stream ea shannon-1.6-lite, shannon-1.6-pro, shannon-coder-1 kapa lelapa la Shannon 3 e fela ka finish_reason: "length" ha karabo e khaoloa moeling oa eona.

Meeli le balance

Hore na theko e thehoa joang

• Litheko li ka USD ka tokens tse 1,000,000. Balance ea hau e baloa ka tokens tse lekanang le $5.00 ka 1,000,000, kahoo theko ea model e re balance e kae e nkoang ke tokens tsa eona.
• Li-model tsa Shannon li na le theko e le 'ngoe. Kopo e lefisoa usage.total_tokens ka theko eo.
• Li-model tse hosted tsa open-weight li na le litheko tse tharo. Input e baloang ho prompt cache e lefisoa ka theko ea cached, e leng 25% ea theko ea input e hlatsoetsoeng ho $0.001. Karolo e setseng ea input e lefisoa ka theko ea input, output ka theko ea output.
• Li-model tse hosted tsa open-weight li bala tokens ka tokenizer ea model e 'ngoe le e 'ngoe. GET /v1/models e supa sena e le tokenizer: "original".
• shannon-coder-1 e baloa ka likopo, eseng ka tokens, ho /v1/chat/completions le /v1/messages. Theko ea eona e thathamisitsoeng e sebetsa ho /v1/responses.

Seo kopo e se behelang thoko, mehlala e sebelitsoeng ea tefo le allowance ea likopo tsa Shannon Coder li leqepheng la Meeli le balance. Meeli le balance

Li-id tsa li-model

Romela e 'ngoe ea li-id tsena e le 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

• Litlhaku tse kholo le tse nyane ha li bohlokoa, mme libaka tse pota-potileng id lia tlosoa: SHANNON-3 le shannon-3 ke model e le 'ngoe.
• Karabo kamehla e nka id e phatlalalitsoeng ho model, ho sa tsotellehe hore na u rometse mongolo ofe.
• Lebitso la ho bontša, le kang Shannon 3, hase id.

Mengolo e mene e khutšoanyane le eona e amohelwa.

Id e sa phatlalatsoang e arajoa ka boemo ba 400, mofuta invalid_request_error le molaetsa unknown model: <id> ho li-endpoint tse tharo tsohle. Ha ho model e 'ngoe e arabang sebakeng sa eona.

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

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

• Kamehla romela model. /v1/responses e araba kopo e se nang eona ka 400. Ho /v1/chat/completions le /v1/messages kopo e joalo e arajoa ke shannon-1.6-lite.
• POST /v1/tokenize le POST /v1/messages/count_tokens li amohela li-id tsa li-model tse hosted tsa open-weight.

Thathamisa li-model

GET /v1/models e khutlisa li-model tsa leqephe lena e le JSON, e nang le context window, litheko le bokhoni bo tšoanang. E sebelise ho tlatsa model picker kapa ho hlahloba theko ho code.

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"

Karabo, e khutsufalitsoeng ho entry e le 'ngoe ea mofuta o mong le o mong:

{
  "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"
      ]
    }
  ]
}

• GET /v1/models ha e hloke senotlolo. Karabo e tšoana bakeng sa moletsi e mong le e mong mme ha e itšetlehe ka plan ea hau.
• Lenane le na le li-id tse ka bitsoang. Model e sa khoneng ho sebeletsa hajoale e siuoa ho lona.
• Ha ho endpoint ea model e le 'ngoe: GET /v1/models/{id} e araba ka 404 le mofuta not_found_error.