Last refreshed 2026-06-29. Next refresh: weekly.
Why use Trinity Mini on Vercel AI Gateway?
Vercel AI Gateway offers Trinity Mini with pay-as-you-go pricing at $0.04/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Trinity Mini across 3 providers to find the best fit for your use caseInput / 1M
$0.045
Output / 1M
$0.15
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
arcee-ai/trinity-miniRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="arcee-ai/trinity-mini",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "arcee-ai/trinity-mini", not the LLMReference slug "trinity-mini".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Trinity Mini Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Arcee AI | — | — |
| OpenRouter | $0.04 | $0.15 |
| Vercel AI Gateway | $0.04 | $0.15 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.04 |
| Output tokens | $0.15 |
Capabilities
JSON / Tool useStructured Outputs
About Trinity Mini
26B sparse MoE with 3B active parameters per token and 128K context window. Trained on 10T tokens. Fully post-trained for reasoning and instruction following, suitable for cloud or on-premises deployment. Available via Arcee AI API and OpenRouter.
Get Started
Model Specs
Released2025-12-01
Parameters26B
Context128k
ArchitectureMixture of Experts