Nkọwa API

Akụrụngwa nke Uche Na-enweghị Mmachi

API AI na-enweghị mmachi: model Shannon na-enweghị ọjụjụ na enweghị filter, sitere na GPU anyị n'onwe anyị. Kwekọrọ na OpenAI na Anthropic — jiri SDK i ji ugbu a, otu key, streaming, tool calling na reasoning n'endpoint ọ bụla.

22 model na-enweghị mmachi
256K context window
site na $0.50/1M
3 API ndị kwekọrọ
3 netwọk: TLS, Tor, I2P

Malite iwu Nwale 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
  }'

Models & ọnụahịa KWA 1M TOKENS

Oke, id na otu esi emepụta ọnụahịa

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

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Enweghị mmachi

Model nwere ọkwa flagship maka reasoning miri emi na output ogologo.

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

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$1.95 / $0.488 / $3.90

Ndị ọzọ
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Enweghị mmachi

Model generalist siri ike nwere output multilingual bara ọgaranya.

Model id GLM-5.2-3BIT-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.73 / $0.183 / $2.34

Ndị ọzọ
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Enweghị mmachi

Model dị elu e debere maka azịza zuru ezu, nwere nkọwa.

Model id Kimi-K3-3BIT-REAP

Context
256K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$3.83 / $0.958 / $19.12

Ndị ọzọ
Nemotron3Ultra 3BIT-REAP

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

Enweghị mmachi

Model buru ibu dị irè nwere reasoning siri ike kwa dọla.

Model id Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.75 / $0.188 / $3.30

Ndị ọzọ
MiniMax-M3 3BIT-REAP

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

Enweghị mmachi

Model ngwa ngwa, dị ọnụ maka ọrụ dị ukwuu n'ọnụ ọgụgụ.

Model id MiniMax-M3-3BIT-REAP

Context
256K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ
DeepSeek-V4-Flash-0731 W4A16-AUTOROUND-REAP

DeepSeek · 284B MoE · 13B active

Enweghị mmachi

Model DeepSeek ngwa ngwa na-edozi ọsọ na àgwà.

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

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Enweghị mmachi

Model nwere ike maka reasoning na ide draft kwa ụbọchị.

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

Context
256K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.78 / $0.195 / $3.67

Ndị ọzọ
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Enweghị mmachi

Model dị ọnụ nke ukwuu maka ọrụ dị mfe.

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

Context
256K

Input
Text na input

Structured output
Enweghị structured output
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Enweghị mmachi

Model okike nwere olu ide pụrụ iche.

Model id inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Text + foto na input

Structured output
JSON object
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$1.42 / $0.355 / $6.07

Ndị ọzọ
MiMo-V2.5-Pro W8A16

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

Enweghị mmachi

Model pro dị nta maka output nwere nhazi na nkenke.

Model id MiMo-V2.5-Pro-W8A16

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Enweghị mmachi

Model obere, dị ngwa maka ọrụ dị mfe na ọnụ kachasị ala.

Model id MiMo-V2.5-W8A16

Context
256K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ
Hy3 W8A16

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

Enweghị mmachi

Model dị ọnụ maka azịza mkparịta ụka dị mkpirikpi.

Model id Hy3-W8A16

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kwa 1M

$0.50 / $0.125 / $2.00

Ndị ọzọ

Models Shannon otu ọnụego nkwụsi ike maka input na output

Shannon 1.6 Lite

Enweghị mmachi

Azịza ngwa ngwa, dị irè maka ọrụ kwa ụbọchị

Model id shannon-1.6-lite

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.90
Shannon 1.6 Pro

Enweghị mmachi

Reasoning dị elu maka nsogbu dị mgbagwoju anya

Model id shannon-1.6-pro

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$7.80
Shannon 2 Lite

Enweghị mmachi

Shannon 2 Lite: pipeline think-draft-review ngwa ngwa nwere reasoning trace a na-ahụ anya. Chat kwa ụbọchị, nchịkọta na Q&A.

Model id shannon-2-lite

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.90
Shannon 2 Pro

Enweghị mmachi

Shannon 2 Pro: ngafe think-draft-review miri emi maka nyocha, ide ọdịnaya ogologo na reasoning nke nzọụkwụ dị iche iche.

Model id shannon-2-pro

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$5.85
Shannon 3

Enweghị mmachi

Model Shannon nke ọgbọ kachasị ọhụrụ nwere reasoning ngwa ngwa na ọnụahịa dị ala nke a kwadoro.

Model id shannon-3

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.35
Shannon 3 Pro

Enweghị mmachi

Ọkwa Shannon 3 nwere ikike dị elu maka ọrụ dị mgbagwoju anya nke nzọụkwụ dị iche iche.

Model id shannon-3-pro

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.35
Shannon 3.1

Enweghị mmachi

Shannon 3 na ngwaọrụ anyị n'onwe anyị, na-eme streaming n'ọsọ zuru ezu na-enweghị rate gate.

Model id shannon-3.1

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.35

Ndị ọzọ
Shannon 3.1 Pro

Enweghị mmachi

Reasoning miri emi n'ọsọ zuru ezu nwere ngafe nyocha n'azụ maka ajụjụ siri ike.

Model id shannon-3.1-pro

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Ọnụahịa / 1M tokens

$3.35

Ndị ọzọ
Shannon 3.5

Enweghị mmachi

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

Model id shannon-3.5

Context
192K

Input
Text + foto na input

Structured output
JSON schema
- Tools
- Streaming
Ọnụahịa / 1M tokens

$3.35

Ndị ọzọ
Shannon Coder 1

Enweghị mmachi

Ọkachamara na koodu na tools: agentic editing, faịlụ ogologo, na tool loops siri ike.

Model id shannon-coder-1

Context
128K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Streaming
Ọnụahịa / 1M tokens

$8.00

Chọgharịa docs

Enwere ike ịbanye site na Tor na I2P Onion service, I2P eepsite na encrypted TLS mirror. Otu /v1 routes, otu key, streaming gụnyere; enweghị cookies, enweghị JavaScript, enweghị request sitere n'aka ndị ọzọ. Endpoint Tor & I2P

Kwadebere ịrụ?

Akaụntụ ọ bụla nwere free tier. Key gị dị otu pịa.

Mepụta igodo API Lee akwụkwọ

Akụrụngwa nke Uche Na-enweghị Mmachi

Models & ọnụahịa KWA 1M TOKENS

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

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`

Models Shannon otu ọnụego nkwụsi ike maka input na 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

Chọgharịa docs

Kwadebere ịrụ?

Models & ọnụahịa KWA 1M TOKENS

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

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

Models Shannon otu ọnụego nkwụsi ike maka input na 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

Chọgharịa docs

Kwadebere ịrụ?

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`