> ## Documentation Index
> Fetch the complete documentation index at: https://docs.valiancehealth.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Models
> The full model catalog the gateway serves, grouped by provider, with the processor and assessment status of every model.
The gateway serves models from five providers. Every model runs under a signed BAA — AWS or Microsoft. Whatever model you pick, the redaction path is identical: identifiers never reach the model.
**Where each model processes your data is covered by our PDPA Transfer Impact Assessment**, which names every destination. We share it under NDA — ask us, and ask before you build against a model if residency is a requirement for you.
**The assessment is ours to complete, not yours to negotiate.** A model whose destination we have assessed is callable by every customer. One we have not assessed is callable by none, and returns `403` with `code: "model_not_allowed"` until that changes. The **Transfer assessment** column below tells you which is which today.
If you omit `model`, the gateway uses `apac.amazon.nova-pro-v1:0`.
**Read the model ID as a destination, not just a capability.** A prefix names where inference happens: `apac.` is the ten Asia-Pacific AWS regions, `us.` is the United States, `in.` is India, and `jp.` is Japan. A model ID with no such prefix, or with `global.`, is served from a pool that names no single jurisdiction — which is why those cannot carry a completed assessment, whatever their BAA status. A signed BAA covers the *service*; a transfer assessment needs the *country*. Both are required, and they are not the same question.
Every model in this catalog supports [tool calling](/api/tool-calling). Models without tool support are not listed.
## Amazon
| Model ID | Tier | Processor | Transfer assessment |
| ----------------------------- | ------------------ | -------------------------------- | ------------------- |
| `apac.amazon.nova-pro-v1:0` | Standard (default) | AWS Bedrock — BAA, HIPAA-aligned | Complete |
| `apac.amazon.nova-lite-v1:0` | Light | AWS Bedrock — BAA, HIPAA-aligned | Complete |
| `apac.amazon.nova-micro-v1:0` | Micro | AWS Bedrock — BAA, HIPAA-aligned | Complete |
The default family, and the one with a completed assessment. Pick these unless you have a reason not to.
## Anthropic
| Model ID | Tier | Processor | Transfer assessment |
| ------------------------------------------------- | ----------------------- | -------------------------------- | ----------------------------- |
| `global.anthropic.claude-opus-5` | Frontier (most capable) | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
| `global.anthropic.claude-sonnet-5` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
| `global.anthropic.claude-haiku-4-5-20251001-v1:0` | Fast | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
Same AWS account and BAA as the Nova family. The BAA is not the open question — the destination is. A `global.` profile routes to whichever region has capacity, so there is no single country to assess, and by the rule above that keeps the assessment Open. An APAC-resident Claude exists on a `jp.` profile and would close it; that route is not served here yet.
## OpenAI
| Model ID | Tier | Processor | Transfer assessment |
| ----------------------------- | ----------------- | -------------------------------- | ----------------------------- |
| `us.openai.gpt-5.6-terra` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Complete — United States |
| `us.openai.gpt-5.6-luna` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Complete — United States |
| `us.openai.gpt-5.6-sol` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Complete — United States |
| `in.openai.gpt-5.6-terra` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Complete — India |
| `in.openai.gpt-5.6-luna` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Complete — India |
| `global.openai.gpt-5.6-terra` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
| `global.openai.gpt-5.6-luna` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
| `global.openai.gpt-5.6-sol` | Frontier | AWS Bedrock — BAA, HIPAA-aligned | Open — no single jurisdiction |
| `openai.gpt-oss-120b-1:0` | Open-weight | AWS Bedrock — BAA, HIPAA-aligned | Open |
| `openai.gpt-oss-20b-1:0` | Open-weight, fast | AWS Bedrock — BAA, HIPAA-aligned | Open |
**The `us.` and `in.` prefixes are the destination.** These are the same GPT-5.6 models, served from a single named jurisdiction — the United States, or India — rather than from a pool. That is what makes their assessment completable, and it is why the prefix is part of the model ID rather than a separate parameter: naming the model names the destination.
Pick `in.` for the shortest chain — one country, one assessment. Pick `us.` for the widest capacity. The `global.` rows are the same three models served from a worldwide pool: same BAA, same processor, but no single country to assess — so they stay Open, and clinical traffic belongs on a prefixed id.
**The GPT-5.6 family retains flagged traffic for up to 30 days.** AWS applies zero data retention to Bedrock by default, but the GPT-5.6 family is an exception: traffic flagged by its abuse classifier is held up to 30 days for automated review, in the region that processed the request. It is not shared with OpenAI. If that does not suit your use case, pick a Nova or `gpt-oss` model — neither carries the exception.
Dialect note: the AWS-served GPT-5.6 route speaks Bedrock Converse. The gateway routes by model ID, so **your request format does not change**.
## DeepSeek
| Model ID | Tier | Processor | Transfer assessment |
| ------------------- | --------- | -------------------------------- | ------------------- |
| `DeepSeek-V4-Flash` | Fast | Azure AI Foundry — Microsoft BAA | Open |
| `deepseek.v3.2` | Reasoning | AWS Bedrock — BAA, HIPAA-aligned | Open |
## MiniMax
| Model ID | Tier | Processor | Transfer assessment |
| ---------------------- | --------- | -------------------------------- | ------------------- |
| `minimax.minimax-m2.5` | Reasoning | AWS Bedrock — BAA, HIPAA-aligned | Open |
Note: this model emits reasoning tokens billed as output, so its cost per task runs above its per-token rate card.
## Choosing a model
```bash theme={null}
curl https://api.v2.healthproximate.com/api/v1/llm/chat/completions \
-H "Authorization: Bearer hpx_..." \
-H "Content-Type: application/json" \
-d '{
"model": "apac.amazon.nova-pro-v1:0",
"messages": [{"role": "user", "content": "Summarize this discharge note: ..."}]
}'
```
**The catalog is the same for every customer.** A model is callable once its destination is covered by our transfer assessment, and refused until then — the same set for everyone, not a per-account menu. Models not yet covered return `403` with `code: "model_not_allowed"`.
There is no region or routing parameter on the request. The model you name determines how it is served, so the model id is the whole choice — not a per-call flag we would have to trust the caller to set.
## Errors you may see
| Status | Code | Meaning |
| ------ | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `403` | `model_not_allowed` | This model's destination is not yet covered by our transfer assessment, so it is not callable by anyone. Pick a model whose **Transfer assessment** reads Complete. |
| `503` | — | The redaction engine is unavailable. The gateway fails closed rather than forward un-redacted text. |
See [Errors & limits](/api/errors-and-limits) for the full error contract.