Trinity Mini

About 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 calling and multi-step agent workflows.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Other Model Lineup

Compare all models from Other to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

GLM 4 32B

Zhipu Ai

Input: $0.10

Output: $0.10

Context: 33k

Pixtral 12B

Mistral

Input: $0.10

Output: $0.10

Context: 4k

Ministral 8B

Mistral

Input: $0.10

Output: $0.10

Context: 128k

Phi 4

Microsoft

Input: $0.06

Output: $0.14

Context: 16k

💡 Cheaper Alternatives

Same Brand (Other)

Cross Brand

🚀 Quick Start

Get started with Trinity Mini API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="arcee-ai/trinity-mini-20251201",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision