Secure
Centralize provider credentials. Issue scoped API keys per team. Rotate or revoke access without touching developer configs.
Control
Set hard budget and rate limits per developer, team, or workspace. Block requests when limits are hit.
Observe
Log every request — cost, tokens, latency, model, and who made it. Attribute spend by team or project.
Supported agents
Claude Code
The most widely deployed AI coding agent. Supports Anthropic direct, Bedrock, and Vertex AI through a single Portkey endpoint.
OpenAI Codex
OpenAI’s terminal coding agent. Configure via
config.toml with full provider flexibility.Cursor
Route Cursor’s AI requests through Portkey for observability and cost controls.
Cline
Set Portkey as Cline’s custom OpenAI base URL.
Roo Code
Drop-in Portkey integration via base URL override.
Goose, opencode & more
Any OpenAI-compatible coding agent works with Portkey.
What platform teams get
Access control
Developers never see provider credentials. Every request is authenticated through a scoped Portkey key.| Goal | What to use | Description |
|---|---|---|
| Centralize credentials | Model Catalog | Store Anthropic, Bedrock, and Vertex keys once. Issue scoped Portkey keys to teams — no raw key distribution. |
| Isolate teams | Workspaces | Each team gets its own workspace with separate budgets, rate limits, and provider access. One team’s usage never affects another’s. |
| Manage team access | API Keys | One key per developer or team. Rotate or revoke from one place without touching developer configs. |
| Provision access at scale | SSO / SCIM | Connect your identity provider. Onboard and offboard developers automatically. |
Cost management
Agentic loops are expensive. One uncapped session can rack up hundreds of dollars overnight.| Goal | What to use | Description |
|---|---|---|
| Cap team spending | Budget Policies | Hard spend limits per developer, team, or workspace. Requests block when the limit is hit. |
| Prevent traffic starvation | Rate Limits | Stop any single user from consuming shared provider capacity. |
| Attribute costs by team | Logs + Metadata | Every request logged with team, project, model, tokens, and exact cost. Answer spend questions in seconds. |
Reliability
Coding agents fail silently when providers go down. Portkey routes around outages automatically.| Goal | What to use | Description |
|---|---|---|
| Survive provider outages | Fallbacks | Auto-retry on Bedrock or Vertex if Anthropic goes down — no developer intervention. |
| Handle team-scale volume | Load Balancing | Distribute traffic across providers and API keys. |
Governance
Coding agents operate with terminal-level access. Portkey adds the control layer.| Goal | What to use | Description |
|---|---|---|
| Protect sensitive codebases | Guardrails | PII detection, prompt injection protection, and content filtering before requests hit the model. |
| Govern MCP tool access | MCP Gateway | Centralized auth and full call logs for every MCP tool your agents use. |
| Maintain a compliance trail | Audit Logs | Immutable record of every access, config change, and policy action across the org. |
| Share coding standards | Agent Skills | Version prompt instructions and sync them to every developer’s agent with one command. |
Setting up Claude Code and Codex
For Claude Code and Codex, the Setup using CLI sets up gateway routing, MCP servers, and team skills in one command:Claude Code setup
Anthropic direct, Bedrock, and Vertex AI
Codex setup
Full
config.toml reference and provider optionsNext steps
Budget Policies
Hard spend limits per team or developer
Model Catalog
Centralized provider credentials and access controls
Configs
Fallbacks, load balancing, and routing strategies
MCP Gateway
Govern MCP tool access across your agent fleet
Observability
Logs, traces, and cost breakdowns for every session
Agent Skills
Sync team coding standards to every developer’s agent