Skip to content

Supported Models#

Lens Agents is designed to be model-agnostic. The platform provides tools, connectivity, and governance; the model provides intelligence. The set of integrated providers expands as customer engagements require.

Currently integrated providers#

As of the current release:

Provider Models How integration works
Anthropic Claude Opus, Sonnet, Haiku Direct Anthropic API
AWS Bedrock Claude, Llama, Mistral, and other Bedrock-hosted models Regional deployment, IAM-based access

Additional providers — including Azure OpenAI, OpenAI direct, Google, and self-hosted endpoints — are configured to customer requirements during evaluation engagements. Tell us during onboarding which providers your deployment requires.

How models work by agent type#

Desktop AI tools#

Desktop tools like Claude Desktop, Cursor, ChatGPT, and Copilot use their own built-in model. Lens Agents has no involvement in the model layer — it provides tools and connectivity via MCP. The user's existing subscription or API key powers the intelligence. This means desktop tools can use any model their vendor supports, independently of what Lens Agents integrates directly.

External agents#

External agents (LangChain, CrewAI, Claude Agent SDK, custom frameworks) bring their own model configuration. The agent developer chooses the provider, model, and parameters. Lens Agents provides the tool execution environment through MCP — the model choice is outside the platform's scope.

Managed agents#

Managed agents route model requests through the platform's LLM proxy. The proxy supports the providers listed above and provides:

  • Usage extraction — token counts (input, output, cache read, cache write) and cost per request
  • Spending enforcement — budget checked before every LLM call. Exceeded budgets return a 429 error.
  • Audit logging — every model request is recorded with model name, token usage, cost, and prompt metadata
  • Prompt caching — stable context sections are cached across invocations to reduce latency and cost

The default model for managed agents is Claude (via AWS Bedrock). The classification model for alert suppression and channel routing is Claude Haiku.

Spending controls#

Spending controls apply to managed agent LLM usage. They do not apply to desktop or external agents, because those agents use their own model provider and billing.

Spending limits can be set at three levels:

Level What it controls
Organization Total LLM spend across all managed agents
Team LLM spend for all managed agents in a team
Agent LLM spend for a single managed agent

When a limit is exceeded, the agent's next LLM request is rejected. Heartbeat monitoring skips gracefully and does not count as an error. Scheduled tasks notify the user that the budget has been exceeded.

Cost visibility#

LLM costs are tracked per request and visible in:

  • Cost Explorer — time-series cost breakdown by agent, team, or organization
  • Audit trail — LLM proxy events include token counts and cost per request
  • Agent overview — each agent's detail page shows 30-day LLM cost

Model configuration for managed agents#

Setting Default
Primary model Claude (via AWS Bedrock)
Classification model Claude Haiku
Temperature 0.3
Max output tokens 16,000 per response
Step limit 100 tool-use steps per invocation
Tool output truncation 30,000 characters per tool call

Prompt caching is applied automatically. Stable prompt sections (identity, workspace files, memory summary) are cached. Dynamic sections (timestamp, heartbeat context, recent messages) are not.