[Arcee AI](/ai-gateway/models/labs/arcee-ai) # Trinity Mini Trinity Mini is a 26B-parameter sparse MoE from Arcee AI with 3B active parameters per forward pass. It handles function calling and multi-step agent workflows at low per-token cost, trained end-to-end in the United States. Your use is subject to Arcee AI's [Terms](https://www.arcee.ai/terms-and-conditions) & [Privacy](https://www.arcee.ai/privacy-policy) Policies. Tool Use [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) AI SDKChat CompletionsMessagesResponses ``` 1import { streamText } from 'ai' 2 3const result = streamText({ 4 model: 'arcee-ai/trinity-mini', 5 prompt: 'Why is the sky blue?' 6}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/trinity-mini) [API](/ai-gateway/models/trinity-mini/api) [About](/ai-gateway/models/trinity-mini/about) [Providers](/ai-gateway/models/trinity-mini/providers) [Uptime](/ai-gateway/models/trinity-mini/uptime) [Status](/ai-gateway/models/trinity-mini/status) [Similar](/ai-gateway/models/trinity-mini/similar) [FAQ](/ai-gateway/models/trinity-mini/faq) ## [Copy link to heading](#playground)Playground Try out Trinity Mini by Arcee AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days. ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75)Qwen 3 32B ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=96&q=75) Qwen 3 32B ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![arcee-ai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Farcee-ai-256.png&w=48&q=75) [Arcee AI](/ai-gateway/models/providers/arcee-ai) Legal:[Terms](https://www.arcee.ai/terms-and-conditions)•[Privacy](https://www.arcee.ai/privacy-policy) | 131K | 131K | | | $0.05/M | $0.15/M | | — | | | | | 12/01/2025 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ## [Copy link to heading](#throughput)Throughput24 hours 1W 1D P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#latency)Latency24 hours 1W 1D P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#uptime)Uptime24 hours 1W 1D 1H Direct request success rate on AI Gateway and per-provider. Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/uptime) for more info. 1W 1D 1H ## [Copy link to heading](#more-models-by-arcee-ai)More models by Arcee AI All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![arcee-ai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Farcee-ai-256.png&w=48&q=75) [arcee-ai/trinity-large-thinking](/ai-gateway/models/trinity-large-thinking) | 262K | 0.5s | | $0.25/M | $0.90/M | | — | | ![arcee-ai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Farcee-ai-256.png&w=48&q=75) | | | | 04/01/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ## [Copy link to heading](#about-trinity-mini)About Trinity Mini Trinity Mini is a sparse mixture-of-experts model with 26B total parameters and 3B active per forward pass. The compact active footprint keeps inference costs low while the full parameter set provides enough capacity for function calling and multi-step agent workflows. Arcee AI trained the model end-to-end in the United States, which teams cite for sovereignty and sourcing reviews. Use https://docs.arcee.ai/language-models/trinity-mini-26b for weights and licensing detail. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: MoE routing keeps active parameters low per token, which helps cost at scale. At $0.045 per million input tokens and $0.15 per million output tokens, stress-test cost against quality on your traffic. - Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-trinity-mini)When to Use Trinity Mini ### Best for - High-volume reasoning routes: Deployments where cost per token is a hard constraint - Structured inference tasks: Reverse engineering or deduction from partial observations - U.S. training provenance: Teams that need domestic-only training for policy or procurement ### Consider alternatives when - Deepest large-model reasoning: Trinity Large Preview offers a larger parameter space at higher cost - Long-term enterprise SLA: This tier does not offer a fixed enterprise support contract - Tight latency budgets: Some workloads rule out even a compact MoE path ## [Copy link to heading](#conclusion)Conclusion Trinity Mini pairs MoE efficiency with U.S. training provenance for teams that balance cost, control, and reasoning depth. Match spend to $0.045 and $0.15, then scale what works.