arcee-ai/trinity-mini
131,072 context · $0.04/M input tokens · $0.15/M output tokens
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Gunakan contoh kode berikut untuk integrasi dengan API kami:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="arcee-ai/trinity-mini",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)arcee-ai trinity-mini
| Specification | Value |
|---|---|
| Provider | Arcee-Ai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 131072 tokens |
| Max Output | 131072 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.0 |
| Output | $0.2 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: arcee-ai/trinity-mini
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="arcee-ai/trinity-mini",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "arcee-ai/trinity-mini",
"messages": [{"role": "user", "content": "Hello!"}]
}'arcee-ai/trinity-mini
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...
Input
$0.045 /M
Output
$0.15 /M
Konteks
131K
Output Maks.
131K
Penggunaan Tool
Didukung
Akses Trinity Mini melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Harga di WaveSpeedAI: $0.04 per juta token input dan $0.15 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Trinity Mini mendukung hingga 131K token konteks dengan hingga 131K token output per permintaan.
Ya. WaveSpeedAI menyediakan Trinity Mini melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Trinity Mini.