> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Example models

> Current text-model choices, provider compatibility, and what documentation validation does not prove.

These documentation defaults were checked against provider catalogs on **October 4, 2026**. Agentium's release version and a provider's model version are independent.

## Text models used in examples

| Workload | Example model ID | Override |
| - | - | - |
| General OpenAI agent and harness | `gpt-6.1-sol` | `OPENAI_MODEL` |
| Focused, lower-cost OpenAI tasks | `gpt-6-luna` | `OPENAI_FAST_MODEL` |
| Demanding OpenAI reasoning/coding | `gpt-6-astra` | Explicit application choice |
| General Anthropic agent | `claude-sonnet-5-5` | `ANTHROPIC_MODEL` |
| Heavier Anthropic reasoning | `claude-opus-5-5` | Explicit application choice |
| General Gemini agent | `gemini-3.8-flash` | `GOOGLE_MODEL` |

These selections follow the providers' published model catalogs: [OpenAI](https://developers.openai.com/api/docs/models), [Anthropic](https://platform.claude.com/docs/en/models/overview), and [Google](https://ai.google.dev/gemini-api/docs/models). Check account access, region, and pricing before deploying. The environment names above are conventions used by the example code, not automatic Agentium configuration.

## Keep the endpoint and parameters compatible

* **OpenAI:** v4 routes GPT-6 function-tool calls through Responses. It drops unsupported sampling fields for reasoning models. Use a supported effort; Astra and Sol do not offer `none`, while Luna does. A custom OpenAI-compatible gateway must implement the endpoint the adapter selects.
* **Anthropic:** v4 uses adaptive thinking for Claude 5 when reasoning is enabled. Use `effort` for these examples; an older `budgetTokens` recipe does not set a fixed thinking budget on the adaptive path.
* **Gemini:** v4 maps Gemini 3 reasoning effort to thinking level and removes sampling fields for Gemini 3.8. A Gemini 2.5 token-budget example is not the same configuration.
* **Provider continuation:** retain opaque provider history for a tool loop. Switching provider/model may require a new session; do not reuse signed reasoning or tool continuation from a different provider.

## Specialized adapters have their own versions

[Speech models](/voice/adapters) must match the adapter's endpoint and accepted model families. In particular, ElevenLabs stream-input synthesis uses its supported v2 families; replacing that ID with a newer dialogue model would break the example. Embedding dimensions, rerank models, image models, and device models also have independent contracts.

Azure deployment names, Bedrock inference profiles, Vertex regional availability, and third-party gateway IDs remain host configuration. Do not replace them mechanically with a direct API model ID. Historical migration examples and pricing fixtures retain their historical names where they explain old behavior.

## Update cost accounting too

The v4 built-in cost table predates the current GPT-6 examples. Supply matching `CostTracker.pricing` entries when changing models; the [cost recipes](/examples/cost-observability) include dated text-rate overrides. Token usage can be correct while an outdated or missing price makes the dollar estimate wrong.

## What has been checked

Complete examples are type-checked against Agentium v4 declarations. Harness recipes run with deterministic providers to verify tool loops, context, session ownership, events, and cleanup. These checks do not certify live provider behavior or your account's access. Run a small application evaluation before changing the model in a deployed service.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.