Try Bifrost Enterprise free for 14 days. Request access
AI Gateway

Best LLM Gateways for Monitoring Claude Code Token Spend

Best LLM Gateways for Monitoring Claude Code Token Spend
Compare the best LLM gateways for monitoring Claude Code token spend, with per-developer cost tracking, budgets, and real-time token usage visibility.

A single Claude Code session can issue hundreds of model calls across Sonnet, Opus, and Haiku, and without a gateway in front of it, that Claude Code token spend lands on one provider invoice with no per-developer, per-project, or per-model breakdown. Bifrost, the open-source AI gateway built in Go by Maxim AI, is free to self-host and is the best overall choice for engineering teams that need to monitor and control Claude Code token spend across developers, projects, and models. This post compares the LLM gateways that sit between Claude Code and your providers, and explains how each one handles cost tracking, budgets, and token usage visibility. The criteria below focus on what platform teams actually need when Claude Code moves from a few pilot users to an organization-wide rollout.

Why Claude Code Token Spend Is Hard to Monitor

Claude Code talks directly to the Anthropic API by default, which means every request is billed against a single account key with no built-in attribution. When one developer uses it, the cost shows up on one invoice. When a hundred engineers use it concurrently across projects and approval modes, the spend becomes opaque and attribution breaks down.

The specific monitoring gaps that appear at scale are consistent:

  • No per-user attribution. A shared key cannot tell you which developer or team generated which tokens.
  • No budget enforcement. A runaway agent loop on a large codebase can consume thousands of dollars in tokens before anyone notices.
  • No model-level breakdown. Claude Code mixes Sonnet, Opus, and Haiku in a single session, and raw invoices rarely separate spend by tier.
  • No real-time signal. Provider billing dashboards update on a delay, so cost spikes are visible only after they have already happened.

Routing Claude Code through a gateway closes these gaps. By pointing Claude Code at a gateway base URL, every request is intercepted at the network layer and tagged with an identity before it reaches Anthropic. Bifrost supports this by reading a virtual key once the ANTHROPIC_BASE_URL environment variable points Claude Code at the gateway, which requires no change to developer workflows.

What to Look for in an LLM Gateway for Claude Code Cost Tracking

An LLM gateway for Claude Code cost tracking is a control layer that intercepts Claude Code requests, attributes them to an identity, and records token usage and cost before forwarding the call to a model provider. When evaluating gateways for this job, weigh them against the following criteria:

  • Per-identity token tracking: can the gateway attribute token usage and cost to individual developers, teams, or projects, not just one shared key.
  • Budget controls: can it enforce hard spending limits and reject requests once a budget is exhausted.
  • Rate limiting: can it cap requests and tokens per consumer to stop runaway sessions.
  • Real-time observability: does it expose live cost and token metrics rather than delayed billing reports.
  • Multi-provider routing: can it run Claude models across Anthropic, Bedrock, Vertex, and Azure without changing developer workflows.
  • Self-hosting and data control: can it be deployed inside your own infrastructure so request data never leaves your network.

Bifrost meets all six criteria as a free, open-source layer, with governance features available in the open-source build rather than gated behind an enterprise tier.

The Best LLM Gateways for Monitoring Claude Code Token Spend

The gateways below are ranked by how completely they cover the cost-monitoring criteria above for Claude Code specifically.

1. Bifrost

Bifrost is a high-performance, open-source AI gateway that unifies access to 1,000+ models through a single OpenAI-compatible API, and it adds only 11 microseconds of overhead per request at 5,000 requests per second in sustained benchmarks. For Claude Code, it intercepts requests at the network layer and attributes every token to a virtual key, the primary governance entity that carries its own access permissions, budgets, and rate limits. Cost is tracked independently at the customer, team, virtual key, and provider levels, so a platform team can see exactly which developer or project drove which portion of Claude Code token spend. Bifrost runs Claude models across Anthropic, AWS Bedrock, Google Vertex, and Azure, and developers can switch tiers mid-session with the /model command without touching billing.

Best for: Bifrost is built for enterprises running mission-critical AI workloads that require best-in-class performance, scalability, and reliability. It serves as a centralized AI gateway to route, govern, and secure all AI traffic across models and environments with ultra low latency. Bifrost unifies LLM gateway, MCP gateway, and Agents gateway capabilities into a single platform.

Designed for regulated industries and strict enterprise requirements, it supports air-gapped deployments, VPC isolation, and on-prem infrastructure. It provides full control over data, access, and execution, along with robust security, policy enforcement, and governance capabilities.

2. LiteLLM

LiteLLM is an open-source proxy that exposes a unified API across multiple providers and supports basic key-based spend tracking. Teams routing Claude Code through it can attribute usage to API keys and set budgets, though performance overhead and the depth of real-time observability are common evaluation points for high-throughput coding workloads. Teams comparing the two can review Bifrost as a drop-in LiteLLM alternative with a full feature breakdown.

Best for: smaller teams that want a lightweight open-source proxy and do not yet need hierarchical budgets or enterprise governance.

3. Cloudflare AI Gateway

Cloudflare AI Gateway is a hosted proxy that logs requests, caches responses, and reports aggregate analytics for traffic passing through it. It can sit in front of Claude Code requests and surface usage trends, but it is a managed service rather than a self-hosted layer, which matters for teams that need request data to stay inside their own network.

Best for: teams already standardized on Cloudflare that want hosted analytics and caching with minimal setup.

4. OpenRouter

OpenRouter is a model marketplace that aggregates providers behind a single API and reports spend per account. For Claude Code, note that OpenRouter does not always stream tool-call arguments in the format Claude Code expects, which can cause file operations to fail, so it is better suited to chat-style routing than to agentic coding.

Best for: individual developers experimenting with many models through one account, rather than governed team deployments.

5. Kong AI Gateway

Kong AI Gateway extends the Kong API gateway with AI-specific plugins for routing and request logging. Organizations already running Kong for general API management can apply familiar rate-limiting and logging plugins to LLM traffic, though the AI-native governance and per-virtual-key cost attribution that Claude Code rollouts need are not its primary focus.

Best for: infrastructure teams already invested in the Kong ecosystem for general API gateway management.

How Bifrost Tracks Claude Code Token Spend

Bifrost records Claude Code token spend through three layers that work together: identity, metrics, and cost reduction.

The first layer is identity. Each developer or team receives a virtual key, and Claude Code sends that key in the ANTHROPIC_AUTH_TOKEN header. Because every request carries a key, Bifrost attributes token usage and cost to the right consumer automatically. Budgets are checked hierarchically across customer, team, and virtual key levels through Bifrost's hierarchical governance controls, and rate limits cap both tokens and requests per consumer to stop a runaway session before it drains a budget.

The second layer is metrics. Bifrost exposes telemetry through a native Prometheus endpoint that tracks success and error rates, token usage, and real-time cost in USD, with a dedicated bifrost_cost_total metric. Teams can wire this into an existing observability stack using standard OpenTelemetry export or scrape the endpoint with Prometheus and visualize spend in Grafana. Custom labels let teams slice cost by project, environment, or any dimension they inject at request time, and alerts can fire when daily provider cost crosses a threshold.

The third layer is reducing the tokens that get billed in the first place. Semantic caching returns cached responses for semantically similar requests, which cuts repeat-query cost for Claude Code prompts that recur across a codebase. For agentic, tool-heavy sessions, Code Mode lets the model write Python to orchestrate multiple tool calls in one step, which has delivered up to 92% lower token costs for MCP workloads at scale. Together these reduce the token volume that monitoring then has to account for.

For regulated teams, Bifrost Enterprise adds audit logs, RBAC, SSO, and in-VPC deployment, so Claude Code token spend can be tracked under SOC 2, HIPAA, or GDPR requirements without sending request data outside the organization.

Setting Up Claude Code Cost Monitoring with Bifrost

Routing Claude Code through Bifrost takes two environment variables. After running the gateway locally or in your cluster, point Claude Code at it and supply a virtual key:

"env": {
  "ANTHROPIC_BASE_URL": "http://localhost:8080/anthropic",
  "ANTHROPIC_AUTH_TOKEN": "your-virtual-key",
  "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-haiku-4-6",
  "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-4-6"
}

With this configuration, every Claude Code request flows through the gateway, is authenticated by the virtual key, and is recorded against that key's budget and rate limits. No Anthropic account login is required when using the ANTHROPIC_AUTH_TOKEN method, since billing routes through the virtual key. The full setup, including provider-specific model pinning for Bedrock, Vertex, and Azure, is covered in the Claude Code integration guide, and the same pattern applies to other terminal coding agents. Claude Code itself can be installed from the official Anthropic documentation.

Frequently Asked Questions

Does routing Claude Code through a gateway change the developer experience?

No. Claude Code behaves identically; the only change is the base URL and auth token in settings.json. Model switching with /model and standard workflows continue to work, while the gateway adds cost tracking transparently.

Can a gateway track Claude Code spend per developer?

Yes. By issuing each developer a separate virtual key, Bifrost attributes token usage and cost to the individual key, and rolls those costs up to team and customer levels for reporting.

Which providers can serve Claude models through Bifrost?

Claude models run through Anthropic directly, as well as AWS Bedrock, Google Vertex, and Azure. Bifrost routes Claude Code to any of these, and developers can switch providers mid-session without code changes. The full list is in the supported providers documentation.

Is Bifrost free to use for cost monitoring?

Yes. Virtual keys, budgets, rate limits, telemetry, and cost tracking are part of the open-source build. Enterprise features such as RBAC, SSO, and in-VPC deployment are available when teams need them.

Get Started with Bifrost

Monitoring Claude Code token spend comes down to putting an identity-aware gateway between your developers and your providers, then reading the cost and token metrics it records. Bifrost does this as a free, open-source layer with hierarchical budgets, real-time telemetry, and token-reducing features like semantic caching and Code Mode, and it scales to enterprise governance when you need it. Explore the full set of Bifrost resources or book a demo with the Bifrost team to see how it fits your Claude Code rollout.

Read next