Tuhinga API

Te Hanganga a Atamai Kāore he Aukati

Te API AI kāore he aukati: ngā model Shannon kāore he whakakāhoretanga, kāore he tātari, e ratoa ana mai i ō mātou ake GPU. Hototahi ki a OpenAI me Anthropic — whakamahia te SDK kua mōhio koe, kotahi key, streaming, tool calling me reasoning i ia endpoint.

22 model kāore he aukati
256K matapihi horopaki
mai i $0.50/1M
3 API hototahi
3 whatunga: TLS, Tor, I2P

Tīmata te hanga Whakamātau i te Playground

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": "Hello, Shannon!"}
    ],
    max_tokens=1024
)

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: 'Hello, Shannon!' }
  ],
  max_tokens: 1024
});

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

package main

import (
    "context"
    "fmt"
    openai "github.com/sashabaranov/go-openai"
)

func main() {
    config := openai.DefaultConfig("YOUR_API_KEY")
    config.BaseURL = "https://api.shannon-ai.com/v1"
    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "shannon-3",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Hello, Shannon!"},
            },
            MaxTokens: 1024,
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

curl -X POST "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": "Hello, Shannon!"}
    ],
    "max_tokens": 1024
  }'

Ngā model me ngā utu MŌ IA 1M TOKENS

Ngā tepe, ngā id me te āhua o te hanga o ngā utu

Ngā model open-weight hosted Horopaki 262,144-token i ia id; ka whakawāteatia motuhake te input me te output; ka whakaae ia id ki tā te model e tāwhai ana e whakaae ai

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Kāore he aukati

He model tohu-rahi mō te reasoning hōhonu me te output roa.

Model id DeepSeek-V4-Pro-0813-3BIT-REAP

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$1.95 / $0.488 / $3.90

Ētahi atu
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Kāore he aukati

He model whānui kaha me te output reo maha pai.

Model id GLM-5.2-3BIT-REAP

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.73 / $0.183 / $2.34

Ētahi atu
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Kāore he aukati

He model taumata teitei kua whakatikatika mō ngā whakautu whaikiko, taipitopito.

Model id Kimi-K3-3BIT-REAP

Horopaki
256K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$3.83 / $0.958 / $19.12

Ētahi atu
Nemotron3Ultra 3BIT-REAP

NVIDIA · 550B hybrid Mamba-Attention MoE · 55B active

Kāore he aukati

He model nui whai hua me te reasoning kaha mō ia tāra.

Model id Nemotron3Ultra-3BIT-REAP

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.75 / $0.188 / $3.30

Ētahi atu
MiniMax-M3 3BIT-REAP

MiniMax · 428B MoE · 23B active · sparse attention

Kāore he aukati

He model tere, utu iti mō ngā kawenga mahi nui.

Model id MiniMax-M3-3BIT-REAP

Horopaki
256K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu
DeepSeek-V4-Flash-0731 W4A16-AUTOROUND-REAP

DeepSeek · 284B MoE · 13B active

Kāore he aukati

He model DeepSeek tere e whakataurite ana i te tere me te kounga.

Model id DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Kāore he aukati

He model whai pūkenga mō te reasoning me te tuhi tauira o ia rā.

Model id Kimi-K2.6-W4A16-AUTOROUND-REAP

Horopaki
256K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.78 / $0.195 / $3.67

Ētahi atu
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Kāore he aukati

He model utu iti rawa mō ngā mahi māmā.

Model id Laguna-S-2.1-W4A16-AUTOROUND-REAP

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
Kāore he output whakatakoto
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Kāore he aukati

He model auaha me tētahi reo tuhi motuhake.

Model id inkling-W4A16-AUTOROUND-REAP

Horopaki
256K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON object
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$1.42 / $0.355 / $6.07

Ētahi atu
MiMo-V2.5-Pro W8A16

Xiaomi · 1.02T MoE · 42B active · 8-bit

Kāore he aukati

He model pro kiato mō te output whakatakoto, tika.

Model id MiMo-V2.5-Pro-W8A16

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Kāore he aukati

He model iti, tere mō ngā mahi ngāwari i te utu iti rawa.

Model id MiMo-V2.5-W8A16

Horopaki
256K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu
Hy3 W8A16

Tencent · 295B MoE · 21B active · 8-bit

Kāore he aukati

He model utu iti mō ngā whakautu kōrero poto.

Model id Hy3-W8A16

Horopaki
256K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
I roto / cached / i waho per 1M

$0.50 / $0.125 / $2.00

Ētahi atu

Ngā model Shannon kotahi te utu paraihe mō te input me te output

Shannon 1.6 Lite

Kāore he aukati

Ngā whakautu tere, pai mō ngā mahi o ia rā

Model id shannon-1.6-lite

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.90
Shannon 1.6 Pro

Kāore he aukati

Mō ngā raruraru uaua: reasoning hōhonu

Model id shannon-1.6-pro

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$7.80
Shannon 2 Lite

Kāore he aukati

Shannon 2 Lite: he paipera whakaaro-tuhinga-arotake tere me tētahi ara reasoning e kitea ana. Mō te chat o ia rā, ngā whakarāpopototanga me ngā pātai-whakautu.

Model id shannon-2-lite

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.90
Shannon 2 Pro

Kāore he aukati

Shannon 2 Pro: ngā wāhanga whakaaro-tuhinga-arotake hōhonu ake mō te tātari, te tuhi roa me te reasoning maha-hikahika.

Model id shannon-2-pro

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$5.85
Shannon 3

Kāore he aukati

Te model Shannon whakatipuranga hou rawa me te reasoning tere i te utu paraihe iti.

Model id shannon-3

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.35
Shannon 3 Pro

Kāore he aukati

Taumata Shannon 3 kaha ake mō ngā mahi uaua, maha-hikahika.

Model id shannon-3-pro

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.35
Shannon 3.1

Kāore he aukati

Shannon 3 i runga i ō mātou ake taputapu, e stream ana i te tere katoa kāore he kuaha rate.

Model id shannon-3.1

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.35

Ētahi atu
Shannon 3.1 Pro

Kāore he aukati

Reasoning hōhonu tere katoa me tētahi wāhanga rangahau muri mō ngā pātai uaua.

Model id shannon-3.1-pro

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Rapu tukutuku
- Streaming
Utu / 1M tokens

$3.35

Ētahi atu
Shannon 3.5

Kāore he aukati

One streaming answer that thinks, searches, draws charts and diagrams and writes files inline.

Model id shannon-3.5

Horopaki
192K

Input
Kuputuhi + whakaahua ki roto

Output whakatakoto
JSON schema
- Tools
- Streaming
Utu / 1M tokens

$3.35

Ētahi atu
Shannon Coder 1

Kāore he aukati

Tohunga mō te code me ngā tools: te whakatika ā-kaiwhakahaere, ngā kōnae roa, me ngā huringa tool ketu.

Model id shannon-coder-1

Horopaki
128K

Input
Kuputuhi ki roto

Output whakatakoto
JSON schema
- Tools
- Reasoning
- Streaming
Utu / 1M tokens

$8.00

Tirotiro i ngā docs

Taea te tae atu mā Tor me I2P He onion service, he I2P eepsite me tētahi whakaata TLS whakamuna. Ōrite ngā ara /v1, ōrite te key, tae atu ki te streaming; kāore he cookies, kāore he JavaScript, kāore he tono a tētahi atu. Ngā endpoint Tor me I2P

Kua reri ki te hanga?

Kei ia pūkete te taumata kore utu. Kotahi anake te pāwhiri ki tō key.

Tikina API key Tirohia ngā utu

Te Hanganga a Atamai Kāore he Aukati

Ngā model me ngā utu MŌ IA 1M TOKENS

Ngā model open-weight hosted Horopaki 262,144-token i ia id; ka whakawāteatia motuhake te input me te output; ka whakaae ia id ki tā te model e tāwhai ana e whakaae ai

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`

Ngā model Shannon kotahi te utu paraihe mō te input me te output

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

Tirotiro i ngā docs

Kua reri ki te hanga?

Ngā model me ngā utu MŌ IA 1M TOKENS

Ngā model open-weight hosted Horopaki 262,144-token i ia id; ka whakawāteatia motuhake te input me te output; ka whakaae ia id ki tā te model e tāwhai ana e whakaae ai

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

Ngā model Shannon kotahi te utu paraihe mō te input me te output

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

Tirotiro i ngā docs

Kua reri ki te hanga?

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`