Amaxwebhu e-API
Iziseko zophuhliso zobukrelekrele Ubukrelekrele Obungenasihluzo
I-API ye-AI engenasihluzo: iimodeli zeShannon ezingenakwala nezingenazihluzo, ezisebenza kwii-GPU zethu. Ihambelana ne-OpenAI ne-Anthropic — faka i-SDK oyisebenzisayo kwangoku, isitshixo esinye, i-streaming, i-tool calling nokuqiqa kuyo yonke i-endpoint.
- 22 iimodeli ezingenasihluzo
- 256K ifestile yomxholo
- ukusuka kwi $0.50/1M
- 3 ii-API ezihambelanayo
- 3 amanethiwekhi: TLS, Tor, I2P
Qalisa ukwakha Zama Ibala lokudlala
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
}'Iimodeli namaxabiso Nge-1M YEE-TOKEN
Imida, ii-id nendlela amaxabiso enziwa ngayoIimodeli ze-open-weight ezisingathiweyo umxholo wee-token ezingama-262,144 kwi-id nganye; i-input ne-output zibhiliwe ngokwahlukeneyo; i-id nganye yamkela oko imodeli eyilinganisayo ikwamkelayo
-
AyinasihluzoDeepSeek-V4-Pro-0813
3BIT-REAPDeepSeek · 1.6T MoE · 49B active
Imodeli yobukhulu be-flagship yokuqiqa okunzulu ne-output ende.
I-id yemodeliDeepSeek-V4-Pro-0813-3BIT-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $1.95 / $0.488 / $3.90
-
AyinasihluzoGLM-5.2
3BIT-REAPZ.ai · 744B MoE · 40B active
Imodeli eqinileyo yeenjongo ezininzi ene-output ecebileyo yeelwimi ezininzi.
I-id yemodeliGLM-5.2-3BIT-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.73 / $0.183 / $2.34
-
AyinasihluzoKimi-K3
3BIT-REAPMoonshot AI · 2.8T MoE · 104B active
Imodeli ephezulu elungiselelwe iimpendulo ezipheleleyo nezineenkcukacha.
I-id yemodeliKimi-K3-3BIT-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $3.83 / $0.958 / $19.12
-
AyinasihluzoNemotron3Ultra
3BIT-REAPNVIDIA · 550B hybrid Mamba-Attention MoE · 55B active
Imodeli enkulu esebenzayo enokuqiqa okuqinileyo ngedola nganye.
I-id yemodeliNemotron3Ultra-3BIT-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.75 / $0.188 / $3.30
-
AyinasihluzoMiniMax-M3
3BIT-REAPMiniMax · 428B MoE · 23B active · sparse attention
Imodeli ekhawulezayo, exabisa kancinci yemithwalo emikhulu.
I-id yemodeliMiniMax-M3-3BIT-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
- Ayinasihluzo
DeepSeek-V4-Flash-0731
W4A16-AUTOROUND-REAPDeepSeek · 284B MoE · 13B active
Imodeli ekhawulezayo ye-DeepSeek elinganisa isantya nomgangatho.
I-id yemodeliDeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
- Ayinasihluzo
Kimi-K2.6
W4A16-AUTOROUND-REAPMoonshot AI · 1T MoE · 32B active
Imodeli enokwenza ukuqiqa kwemihla ngemihla nokuyila imizobo.
I-id yemodeliKimi-K2.6-W4A16-AUTOROUND-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.78 / $0.195 / $3.67
-
AyinasihluzoLaguna-S-2.1
W4A16-AUTOROUND-REAPPoolside · 118B MoE · 8B active
Imodeli exabisa kancinci kakhulu yemisebenzi elula.
I-id yemodeliLaguna-S-2.1-W4A16-AUTOROUND-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- Akukho structured output
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
-
Ayinasihluzoinkling
W4A16-AUTOROUND-REAPThinking Machines · 975B MoE · 41B active
Imodeli yobuchule enelizwi lokubhala elahlukileyo.
I-id yemodeliinkling-W4A16-AUTOROUND-REAP- Umxholo
- 256K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON object
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $1.42 / $0.355 / $6.07
-
AyinasihluzoMiMo-V2.5-Pro
W8A16Xiaomi · 1.02T MoE · 42B active · 8-bit
Imodeli ye-pro ethe cwaka ye-output ecwangcisiweyo nechanekileyo.
I-id yemodeliMiMo-V2.5-Pro-W8A16- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
- Ayinasihluzo
MiMo-V2.5
W8A16Xiaomi · 8-bit multimodal · W8A16
Imodeli encinci, ekhawulezayo yemisebenzi elula ngexabiso eliphantsi kakhulu.
I-id yemodeliMiMo-V2.5-W8A16- Umxholo
- 256K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
-
AyinasihluzoHy3
W8A16Tencent · 295B MoE · 21B active · 8-bit
Imodeli yohlahlo lwabiwo-mali yeempendulo ezimfutshane zencoko.
I-id yemodeliHy3-W8A16- Umxholo
- 256K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-effort yokuqiqa
- I-Prompt caching
- I-Streaming
- Ngek / cached / phuma kwe 1M
- $0.50 / $0.125 / $2.00
Iimodeli zeShannon ixabiso elinye eliqhelekileyo le-input ne-output
-
AyinasihluzoShannon 1.6 Lite
Iimpendulo ezikhawulezayo, ezisebenzayo kwimisebenzi yemihla ngemihla
I-id yemodelishannon-1.6-lite- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.90
- Ayinasihluzo
Shannon 1.6 Pro
Ukuqiqa okuphezulu kwiingxaki ezinzima
I-id yemodelishannon-1.6-pro- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $7.80
- Ayinasihluzo
Shannon 2 Lite
Shannon 2 Lite: umbhobho okhawulezayo wokucinga-ukuyila-ukuphonononga onomkhondo wokuqiqa obonakalayo. Incoko yemihla ngemihla, izishwankathelo ne-Q&A.
I-id yemodelishannon-2-lite- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.90
- Ayinasihluzo
Shannon 2 Pro
Shannon 2 Pro: iindlela ezinzulu zokucinga-ukuyila-ukuphonononga zohlalutyo, ukubhala okude nokuqiqa okunamanyathelo amaninzi.
I-id yemodelishannon-2-pro- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $5.85
- Ayinasihluzo
Shannon 3
Imodeli yeShannon yesizukulwana sakutshanje enokuqiqa okukhawulezayo ngexabiso eliphantsi elinye.
I-id yemodelishannon-3- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.35
- Ayinasihluzo
Shannon 3 Pro
Inqanaba leShannon 3 elinobuchule obuphezulu lomsebenzi onzima onamanyathelo amaninzi.
I-id yemodelishannon-3-pro- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.35
- Ayinasihluzo
Shannon 3.1
Shannon 3 kwihardware yethu, i-streaming ngesantya esipheleleyo ngaphandle kwesithinteli sobuninzi bezicelo.
I-id yemodelishannon-3.1- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.35
- Ayinasihluzo
Shannon 3.1 Pro
Ukuqiqa okunzulu ngesantya esipheleleyo kunomjikelo wophando osemva kwesiza kwimibuzo enzima.
I-id yemodelishannon-3.1-pro- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- Ukufuna kwiwebhu
- I-Streaming
- Ixabiso / 1M yee-token
- $3.35
- Ayinasihluzo
Shannon 3.5
One streaming answer that thinks, searches, draws charts and diagrams and writes files inline.
I-id yemodelishannon-3.5- Umxholo
- 192K
- I-input
- Okubhaliweyo + umfanekiso kungena
- I-structured output
- JSON schema
- Ii-tool
- I-Streaming
- Ixabiso / 1M yee-token
- $3.35
- Ayinasihluzo
Shannon Coder 1
Ingcali yekhowudi nee-tool: ukuhlela kwe-agentic, iifayile ezinde, namaluphu eetool anemigaqo eqinileyo.
I-id yemodelishannon-coder-1- Umxholo
- 128K
- I-input
- Okubhaliweyo kungena
- I-structured output
- JSON schema
- Ii-tool
- Ukuqiqa
- I-Streaming
- Ixabiso / 1M yee-token
- $8.00
Phonononga amaxwebhu
- Ukuqalisa ngokukhawuleza Yenza isitshixo, lathisa i-SDK yakho kwiShannon uze uthumele isicelo sokuqala.
- Iimodeli namaxabiso I-id yemodeli nganye kunye nefestile yayo yomxholo, ii-input nexabiso nge-1M yee-token.
- Uqinisekiso Isitshixo esinye kuyo yonke i-endpoint: i-header ye-Bearer okanye i-x-api-key.
- Umsinga Imisitho ethunyelwe yi-server enee-reasoning delta; ukusetyenziswa kufika kwi-chunk yokugqibela.
- Umsebenzi Ukufowuna Chaza ii-tool, vumela imodeli izibize, yiqhube nge-tool_choice.
- Iziphumo ezicwangcisiweyo Iimpendulo njenge-JSON object okanye ngokwe-JSON schema yakho.
- I-effort yokuqiqa Funda umsinga wokuqiqa; setha i-effort kwiimodeli ze-open-weight ezisingathiweyo.
- I-Prompt caching Iimodeli ezisingathiweyo zigcina ngokuzenzekelayo ii-prefix zeeprompt eziphindaphindwayo, kwi-25% yexabiso le-input.
- I-Responses API Ulwimi lwe-OpenAI Responses kwiimodeli ezifanayo nesitshixo esifanayo.
- Ubume beAnthropic Gcina i-SDK yakho ye-Anthropic nekhowudi ye-Messages; tshintsha i-base URL kuphela.
- Izixhobo zekhowudi ze-CLI I-Claude Code ne-Codex CLI nge-Shannon njengemodeli engasemva kwazo.
- Ukuphatha imposiso Iikhowudi zesimo, iindidi zeempazamo nemo yomzimba wempazamo.
Ukulungele Ukwakha?
Inqanaba lasimahla lifakwe kuyo yonke iakhawunti. Isitshixo sakho siyiklikhi enye kude.