Bring Your Own Model — Setup Guide

Use your own API keys to add models alongside TruVerifAI's four default providers. Each guide below covers where to get the key, what model IDs work, and what to paste into the BYOM form.

Open Bring Your Own Model →

Provider comparison

9 providers · 9 wire protocols

Provider	Setup	Models supported
OpenAI direct	Easy	All chat models
Anthropic direct	Easy	All chat models
Google AI Studio	Easy	Gemini family
Together AI	Easy	Llama, Mistral, Qwen, ...
OpenRouter	Easy	200+ from many providers
Fireworks	Easy	Open-weight chat models
Ollama (local)	Easy	Whatever you pull locally
AWS Bedrock	Medium · IAM	Nova, Llama, Mistral, Titan, Claude, custom imports
GCP Vertex AI	Hard · GCP	Gemini, Claude, DeepSeek, Llama, Mistral

Which wire protocol?

The wire protocol tells TruVerifAI how to talk to your model's host. Pick it by where the model runs:

A first-party account — OpenAI, Anthropic, or Google AI Studio: pick the matching named protocol.
An OpenAI-compatible aggregator — Together, OpenRouter, Fireworks, Groq, a local Ollama: pick OpenAI-compatible and set the Base URL the host documents.
AWS Bedrock — use AWS Bedrock for any model (Nova, Llama, Mistral, Titan, Cohere, custom imports). Use AWS Bedrock — Claudeonly for Claude models — it routes through Claude's native API for the full feature set.
GCP Vertex AI — use GCP Vertex AI — Gemini only for Gemini, GCP Vertex AI — Claude for Claude on Vertex, and GCP Vertex AI — Other models for anything else in Model Garden (DeepSeek, Llama, Mistral, ...).

OpenAI direct

1Sign in to platform.openai.com.
2API keys → Create new secret key.
3Copy the key (starts with sk-...).
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: OpenAI (api.openai.com).
6API Key: paste your sk-... key.
7Model ID: e.g. gpt-4o, gpt-4-1106-preview, or any chat model_id from platform.openai.com/docs/models.
8Click Test & add.

Anthropic direct

1Sign in to console.anthropic.com.
2API Keys → Create Key.
3Copy the key (starts with sk-ant-...).
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: Anthropic (api.anthropic.com).
6API Key: paste your sk-ant-... key.
7Model ID: e.g. claude-3-5-sonnet-20241022, claude-3-opus-20240229, or any chat model_id from docs.anthropic.com.
8Click Test & add.

Google AI Studio

1Go to aistudio.google.com → Get API key.
2Create API key in new project (or pick existing).
3Copy the key.
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: Google AI Studio.
6API Key: paste your key.
7Model ID: e.g. gemini-2.0-flash, gemini-1.5-pro, or any Gemini chat model_id from ai.google.dev/models.
8Click Test & add.

Note: Google AI Studio is the free / direct API. Vertex AI is the enterprise option — see the Vertex section below.

Together AI

1Sign in to api.together.xyz.
2Settings → API Keys → Generate key.
3Copy the key.
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: OpenAI-compatible (Together, OpenRouter, ...).
6API Key: paste your Together key.
7Base URL: https://api.together.xyz/v1
8Model ID: use Together's catalog format, e.g. meta-llama/Llama-3.1-70B-Instruct-Turbo. Find full IDs at docs.together.ai.
9Click Test & add.

OpenRouter

1Sign in to openrouter.ai.
2Keys → Create Key.
3Copy the key (starts with sk-or-...).
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: OpenAI-compatible.
6API Key: paste your sk-or-... key.
7Base URL: https://openrouter.ai/api/v1
8Model ID: use OpenRouter's routing prefix format, e.g. anthropic/claude-3-5-sonnet or meta-llama/llama-3.1-70b-instruct. Full catalog at openrouter.ai/models.
9Click Test & add.

Note: OpenRouter is a unified gateway to 200+ models from many providers. Useful for trying obscure or open-weight models without managing each provider's account.

Fireworks

1Sign in to fireworks.ai.
2Account → API Keys → New API key.
3Copy the key.
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: OpenAI-compatible.
6API Key: paste your Fireworks key.
7Base URL: https://api.fireworks.ai/inference/v1
8Model ID: use Fireworks' account-scoped format, e.g. accounts/fireworks/models/llama-v3p1-70b-instruct. Catalog at fireworks.ai/models.
9Click Test & add.

Ollama (local)

1Install Ollama from ollama.com.
2Run a model locally: ollama pull llama3.1 && ollama run llama3.1
3Confirm the local OpenAI-compatible endpoint is reachable at http://localhost:11434/v1
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: OpenAI-compatible.
6API Key: any non-empty string (Ollama ignores it but the form requires a value).
7Base URL: http://localhost:11434/v1
8Model ID: the local model name (e.g. llama3.1, mistral, qwen2.5-coder).
9Click Test & add.

Note: Local Ollama only works when TruVerifAI is running on the same machine as Ollama. For shared usage, expose Ollama behind a tunnel (cloudflared, ngrok) and use the tunnel URL as the Base URL.

AWS Bedrock

The picker has two AWS options: AWS Bedrock (the Converse API — works for any Bedrock model: Llama, Nova, Mistral, Titan, Cohere, custom imports) and AWS Bedrock — Claude (Claude through the native Anthropic API, for full Claude features). Both use the same AWS credentials.

1In the AWS console: Bedrock → Model access → enable the models you want. Anthropic Claude needs a short use-case form; Amazon Nova and Meta Llama are usually instant.
2IAM → create a user with an inline policy allowing bedrock:InvokeModel, bedrock:InvokeModelWithResponseStream, bedrock:Converse, bedrock:ConverseStream.
3Create an access key for that user (use case: application running outside AWS).
4In TruVerifAI: Bring Your Own Model → Add custom model.
5Wire protocol: AWS Bedrock, or AWS Bedrock — Claude for a Claude model.
6Paste the Access Key ID and Secret Access Key. Leave Session Token blank unless you use temporary STS credentials.
7Region: the region where you enabled the model, e.g. us-east-1.
8Model ID: the Bedrock model id, e.g. amazon.nova-lite-v1:0. Newer models need a cross-region inference profile — prefix the id with the region group, e.g. us.anthropic.claude-sonnet-4-5-20250929-v1:0.
9Click Test and add.

Note: A failure mentioning on-demand throughput means the model needs a cross-region inference profile — prefix the model id with us., eu. or apac. for your region group.

GCP Vertex AI

The picker has three Vertex options: GCP Vertex AI — Gemini only (Gemini models), GCP Vertex AI — Claude (Claude on Vertex), and GCP Vertex AI — Other models (DeepSeek, Llama, Mistral and other OpenAI-compatible Model Garden models). All three authenticate with the same service-account JSON key.

1In the GCP console: enable the Vertex AI API for your project.
2For Claude or an Other-models pick: Vertex AI → Model Garden → open the model card → Enable (one-time). Gemini base models need no enablement.
3IAM and Admin → Service Accounts → create one with the Vertex AI User role (roles/aiplatform.user).
4Create a JSON key for that service account and download it.
5In TruVerifAI: Bring Your Own Model → Add custom model.
6Wire protocol: GCP Vertex AI — Gemini only, GCP Vertex AI — Claude, or GCP Vertex AI — Other models.
7Paste the entire service-account JSON, plus your project ID.
8Region: for Gemini use a regional one like us-central1, or global for newer 3.x models. For Claude use the region its Model Garden card lists — usually us-east5.
9Model ID: the bare model name — gemini-2.5-flash for Gemini, claude-haiku-4-5@20251001 for Claude (note the @date suffix), or the publisher/model-id form for an OpenAI-compatible Model Garden model — e.g. meta/llama-4-maverick-17b-128e-instruct-maas or deepseek-ai/deepseek-v3.2-maas. Strip any publishers/.../models/ wrapper the GCP console shows; the bare model name alone (without the publisher) does NOT work.
10Click Test and add.

Note: Claude on Vertex needs a non-zero token quota for the model in your GCP project — a fresh project often starts at 0. Request an increase under IAM and Admin → Quotas before adding the BYOM, or Test and add will fail with a rate-limit error.

Common pitfalls

Bedrock, on-demand throughput error: newer models reject the bare model id — prefix it with the region group (us., eu., apac.).
Bedrock, model not enabled: the model must be enabled for that exact region under Bedrock → Model access.
Vertex, use the bare model name: gemini-2.5-flash, not the publishers/google/models/... path the console shows.
Vertex, region matters: newer Gemini models are often only on global; Claude on Vertex is region-locked, usually us-east5. A not-servable-in-region error means switch to the region the Model Garden card lists.
Vertex, Claude quota: a new GCP project often has a zero token quota for Claude — request an increase before testing.
Vertex Other Models, id format: use the bare publisher/model-id like meta/llama-4-maverick-17b-128e-instruct-maas. The GCP console often shows publishers/meta/models/... or just the model name without the publisher prefix — neither works.
Vertex Other Models, region: global is correct for DeepSeek V3.2; us-west2is common for Llama / Mistral MaaS. Check the Model Garden card's code snippet for the region the model actually serves on.

Questions about a provider not listed here? The OpenAI-compatible wire protocol works with any host that implements the /v1/chat/completions endpoint — set the Base URL to whatever the host documents.