Providers
A provider is the AI runtime that powers an agent. Exponential is provider-neutral — you're not locked into one AI vendor. Different agents can use different providers, and you can switch providers per task.
Supported providers
| Provider | Company | Default Model | Best for |
|---|---|---|---|
| Claude | Anthropic | Opus | General-purpose, coding, analysis, writing |
| Gemini | Gemini 2.5 Pro | Alternative runtime, Google ecosystem | |
| Codex | OpenAI | GPT-5.4 | OpenAI ecosystem, specific model preferences |
| GLM | Z.AI | GLM-5.1 | Chinese language tasks, Z.AI ecosystem |
Setting up providers
Claude (recommended)
Claude is the default provider and the most deeply integrated.
- Go to Settings → Providers → Claude.
- Follow the authentication instructions.
- Select your preferred model (Opus, Sonnet, or Haiku).
Available models:
| Model | Best for |
|---|---|
| Opus | Complex tasks, deep reasoning, high-quality output |
| Sonnet | Balanced speed and quality, everyday tasks |
| Haiku | Fast tasks, simple operations, high throughput |
Gemini
- Install the Gemini CLI on your machine.
- Go to Settings → Providers → Gemini.
- Authenticate with your Google account.
Available models: Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite.
Codex
- Install the Codex CLI on your machine.
- Go to Settings → Providers → Codex.
- Authenticate with your OpenAI account.
Available models: GPT-5.4, GPT-5.4 Mini, and others.
GLM
- Go to Settings → Providers → GLM.
- Enter your Z.AI API key directly in Exponential.
Available models: GLM-5.1, GLM-5, GLM-4.7, GLM-4.5 Air.
How providers work
When an agent runs, Exponential:
- Takes the agent's system prompt (Personality + Knowledge + Principles)
- Sends it to the selected provider's runtime
- Gives the agent access to MCP tools (comment, propose plan, etc.)
- Streams the agent's output back to the task activity timeline
The experience is the same regardless of provider — agents plan, you approve, they execute, you review. The provider only affects the underlying AI model's capabilities.
Choosing a provider
For most users, Claude is the recommended default. It's the most capable option and has the deepest integration with Exponential.
Consider alternatives when:
- You have existing credits or subscriptions with another provider
- A specific model performs better for your use case
- You want to compare outputs across providers
- You're working in a language or domain where another model excels
Provider per agent
Each agent can specify its own provider in the .agent file:
runtime:
provider: gemini
model: gemini-2.5-proIf no provider is specified, the agent uses the system default (Claude).
Usage monitoring
Exponential tracks provider usage so you can monitor consumption:
- Session usage — tokens used in the current 5-hour window
- Weekly usage — tokens used over 7 days
Usage bars in Settings show your current consumption with color coding — green when healthy, red when approaching limits.