Models & ọnụahịa

model na-enweghị mmachi

22

context window

256K

site na

$0.50 /1M

Hosted open-weight models

context nke tokens 262,144 na id ọ bụla; input na output na-akwụ ụgwọ n'otu n'otu; id ọ bụla na-anabata ihe model ọ na-eṅomi na-anabata

Model	Input	Structured output	In / cached / out kwa 1M	Ndị ọzọ
DeepSeek-V4-Pro-08133BIT-REAPDeepSeek · 1.6T MoE · 49B activeEnweghị mmachi	Text na input	JSON schema	$1.95 / $0.488 / $3.90	Ndị ọzọ
GLM-5.23BIT-REAPZ.ai · 744B MoE · 40B activeEnweghị mmachi	Text na input	JSON schema	$0.73 / $0.183 / $2.34	Ndị ọzọ
Kimi-K33BIT-REAPMoonshot AI · 2.8T MoE · 104B activeEnweghị mmachi	Text + foto na input	JSON schema	$3.83 / $0.958 / $19.12	Ndị ọzọ
Nemotron3Ultra3BIT-REAPNVIDIA · 550B hybrid Mamba-Attention MoE · 55B activeEnweghị mmachi	Text na input	JSON schema	$0.75 / $0.188 / $3.30	Ndị ọzọ
MiniMax-M33BIT-REAPMiniMax · 428B MoE · 23B active · sparse attentionEnweghị mmachi	Text + foto na input	JSON schema	$0.50 / $0.125 / $2.00	Ndị ọzọ
DeepSeek-V4-Flash-0731W4A16-AUTOROUND-REAPDeepSeek · 284B MoE · 13B activeEnweghị mmachi	Text na input	JSON schema	$0.50 / $0.125 / $2.00	Ndị ọzọ
Kimi-K2.6W4A16-AUTOROUND-REAPMoonshot AI · 1T MoE · 32B activeEnweghị mmachi	Text + foto na input	JSON schema	$0.78 / $0.195 / $3.67	Ndị ọzọ
Laguna-S-2.1W4A16-AUTOROUND-REAPPoolside · 118B MoE · 8B activeEnweghị mmachi	Text na input	Enweghị structured output	$0.50 / $0.125 / $2.00	Ndị ọzọ
inklingW4A16-AUTOROUND-REAPThinking Machines · 975B MoE · 41B activeEnweghị mmachi	Text + foto na input	JSON object	$1.42 / $0.355 / $6.07	Ndị ọzọ
MiMo-V2.5-ProW8A16Xiaomi · 1.02T MoE · 42B active · 8-bitEnweghị mmachi	Text na input	JSON schema	$0.50 / $0.125 / $2.00	Ndị ọzọ
MiMo-V2.5W8A16Xiaomi · 8-bit multimodal · W8A16Enweghị mmachi	Text + foto na input	JSON schema	$0.50 / $0.125 / $2.00	Ndị ọzọ
Hy3W8A16Tencent · 295B MoE · 21B active · 8-bitEnweghị mmachi	Text na input	JSON schema	$0.50 / $0.125 / $2.00	Ndị ọzọ

Models Shannon

otu ọnụego nkwụsi ike maka input na output

Model	Context	Input	Structured output	Ọnụahịa / 1M tokens
Shannon 1.6 Liteshannon-1.6-liteEnweghị mmachi	192K	Text + foto na input	JSON schema	$3.90
Shannon 1.6 Proshannon-1.6-proEnweghị mmachi	192K	Text + foto na input	JSON schema	$7.80
Shannon 2 Liteshannon-2-liteEnweghị mmachi	192K	Text + foto na input	JSON schema	$3.90
Shannon 2 Proshannon-2-proEnweghị mmachi	192K	Text + foto na input	JSON schema	$5.85
Shannon 3shannon-3Enweghị mmachi	192K	Text + foto na input	JSON schema	$3.35
Shannon 3 Proshannon-3-proEnweghị mmachi	192K	Text + foto na input	JSON schema	$3.35
Shannon 3.1shannon-3.1Enweghị mmachi	192K	Text + foto na input	JSON schema	$3.35
Shannon 3.1 Proshannon-3.1-proEnweghị mmachi	192K	Text + foto na input	JSON schema	$3.35
Shannon 3.5shannon-3.5Enweghị mmachi	192K	Text + foto na input	JSON schema	$3.35
Shannon Coder 1shannon-coder-1Enweghị mmachi	128K	Text na input	JSON schema	$8.00

Gaa na Quickstart Nwale Playground

Otu esi agụ ahịrị

Model ọ bụla na-eme streaming ma nwee ike ikpọ tools. Atụmatụ ndị ọzọ nke API ka akọwara na peeji Capabilities. Ikike

Context window na output limits

• Context window na-ekpuchi ihe niile model na-agụ maka otu azịza: ozi gị, tool definitions na images.
• Shannon 3 family na-eme ka mkparịta ụka ka ogologo baa n'onwe ya: ọ na-edebe turns ọhụrụ kacha ndị na-abanye n'ime window ma zaa.
• Na stream, a na-akọ prompt toro ogologo dị ka error frame nwere ụdị invalid_request_error na code: "context_length_exceeded".
• max_tokens na-anara uru site na 1 ruo 65,536 na model ọ bụla; max_output_tokens na GET /v1/models bụ elu nke oke ahụ. Default bụ 4,096.
• Na model ọ bụla, max_tokens bụ ego request na-edebe site na balance gị.
• Dị ka oke maka ogologo azịza, hosted open-weight models, shannon-1.6-lite, shannon-1.6-pro na shannon-coder-1 na-etinye max_tokens.
• Na hosted open-weight models ọ na-ejedebe ederede azịza. A naghị agụ reasoning tupu azịza megide ya, uru dị n'okpuru 256 na-arụ ọrụ dị ka 256.
• Stream nke shannon-1.6-lite, shannon-1.6-pro, shannon-coder-1 ma ọ bụ Shannon 3 family na-ejedebe na finish_reason: "length" mgbe e bipụrụ azịza na oke ya.

Limits na balance

Otu esi akpụ ọnụahịa

• Ọnụahịa dị na USD kwa tokens 1,000,000. A na-agụ balance gị na tokens bara uru $5.00 kwa 1,000,000, ya mere ọnụahịa model na-ekwu ole balance tokens ya na-ewe.
• Shannon models nwere otu ọnụahịa. A na-akwụ ụgwọ call maka usage.total_tokens na ọnụahịa ahụ.
• Hosted open-weight models nwere ọnụahịa atọ. A na-akwụ ụgwọ input e sitere na prompt cache gụọ na cached price, nke bụ 25% nke input price gbagoro ruo $0.001. A na-akwụ ụgwọ input ndị ọzọ na input price, output na output price.
• Hosted open-weight models na-agụ tokens site na tokenizer nke model ọ bụla. GET /v1/models na-akaa nke a dị ka tokenizer: "original".
• A na-agụ shannon-coder-1 na calls, ọ bụghị tokens, na /v1/chat/completions na /v1/messages. Ọnụahịa edepụtara ya na-emetụta /v1/responses.

Ihe request na-edebe, ihe atụ nke ụgwọ na Shannon Coder call allowance dị na Limits na balance. Limits na balance

Model ids

Zipụ otu n'ime ids ndị a dị ka 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

• Mkpụrụedemede nta na nnukwu adịghị mkpa, a na-ewepụkwa oghere gburugburu id: SHANNON-3 na shannon-3 bụ otu model.
• Azịza na-ebu id e bipụtara mgbe niile na model, ma ọ bụ ụdị ederede ọ bụla i zipụrụ.
• Aha ngosi dị ka Shannon 3 abụghị id.

A na-anabatakwa ụdị ederede anọ dị mkpụmkpụ.

A na-aza id e bipụtaghị na status 400, ụdị invalid_request_error na ozi unknown model: <id> na endpoints atọ ahụ niile. Enweghị model ọzọ na-aza n'ọnọdụ ya.

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

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

• Zipụ model mgbe niile. /v1/responses na-aza request na-enweghị ya na 400. Na /v1/chat/completions na /v1/messages shannon-1.6-lite na-aza request dị otú ahụ.
• POST /v1/tokenize na POST /v1/messages/count_tokens na-anara hosted open-weight ids.

Depụta models

GET /v1/models na-eweghachi models nke peeji a dị ka JSON, na otu context windows, ọnụahịa na ikike. Jiri ya dejupụta model picker ma ọ bụ lelee ọnụahịa na koodu.

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"

Azịza ahụ, ekelelatara n'otu entry nke ụdị ọ bụla:

{
  "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 achọghị key. Azịza ahụ bụ otu maka onye ọ bụla na-akpọ ma ọ dabereghị na plan gị.
• Ndepụta ahụ nwere ids enwere ike ịkpọ. A na-ahapụ model enweghị ike ijere ozi n'oge a n'ime ya.
• Enweghị endpoint maka otu model: GET /v1/models/{id} na-aza 404 nwere ụdị not_found_error.