agentgateway v1.6.0: Cost Tracking With No Catalog Config

A developer tested agentgateway v1.6.0, released October 2, and found that its built-in LLM pricing catalog delivers per-request cost tracking with no modelCatalog configuration, logging fields such as cost.total=0.000156 for a Claude Sonnet 5 call. The release also adds per-key CEL rate limiting that buckets quota by any request attribute, demonstrated by keying a 3-request-per-60-second limit on the x-api-key header so separate keys never share a bucket.

Originally published at webofmike.com https://webofmike.com/agentgateway-v16-cost-tracking/?utm source=devto&utm medium=syndication&utm campaign=agentgateway-v16-cost-tracking on 2026-10-06. The demo repo and every command in it were run before publishing. agentgateway v1.6.0 https://github.com/agentgateway/agentgateway/releases/tag/v1.6.0 went GA on October 2. Two features are worth a hands-on look before anything else: a built-in LLM pricing catalog that gives you cost tracking with zero configuration, and per-key CEL rate limiting that buckets quota by any request attribute you pick. I ran both against a live gateway and a real Claude Sonnet 5 backend. Code and captured output are in themsquared/agw-16-hands-on https://github.com/themsquared/agw-16-hands-on . I wrote up agentgateway's per-API-key budgets back in v1.5.0 https://webofmike.com/agentgateway-per-key-llm-budgets/ : a budgets list per key, a limit in tokens or USD, and a 429 before the provider ever sees the request. That post also covered the gap underneath it. Budgets only work once the gateway knows what a token costs, and in 1.5 that meant a modelCatalog block naming every model and its per-million-token input and output rate, maintained by hand. v1.6.0 replaces that with a model catalog agentgateway ships and maintains itself. The demo's entire LLM route config: llm: port: 4000 policies: localRateLimit: - type: requests maxTokens: 3 tokensPerFill: 3 fillInterval: 60s key: request.headers "x-api-key" models: - name: claude provider: anthropic params: model: claude-sonnet-5 apiKey: $ANTHROPIC API KEY No modelCatalog anywhere. The access log still produces full cost data because claude-sonnet-5 is a model the built-in catalog already knows: http.status=200 gen ai.usage.input tokens=8 gen ai.usage.output tokens=14 agw.ai.usage.cost.total=0.000156 cost.total=0.000156 cost.rate.input=2 cost.rate.output=10 cost.rate.input and cost.rate.output are USD per million tokens, pulled straight from the catalog. The math checks out: 8 2 + 14 10 / 1,000,000 = 0.000156 . Nothing in the config told agentgateway what this model costs; it already knew. Getting those fields into the access log in the first place is a frontendPolicies.accessLog.add block mapping CEL expressions to log keys: frontendPolicies: accessLog: add: model.requested: llm.requestModel model.served: llm.responseModel tokens.input: llm.inputTokens tokens.output: llm.outputTokens cost.total: llm.cost.total cost.rate.input: llm.costRates.input cost.rate.output: llm.costRates.output Those same CEL fields are what you'd read in a budgets policy from the 1.5 post, so this isn't a separate feature bolted on. It's the same cost-accounting plumbing, now backed by a catalog instead of a hand-maintained table. The second feature in this run is localRateLimit , keyed by a CEL expression rather than a fixed value. The config above keys on request.headers "x-api-key" , with a 3-request bucket that refills every 60 seconds. One rule, evaluated per request, buckets independently per header value: key A, requests 1-3: all 200 http.status=200 ... cost.total=0.000156 ... http.status=200 ... http.status=200 ... key A, request 4, same minute http.status=429 error="rate limit exceeded" reason=RateLimit key B, same minute, different header value http.status=200 ... cost.total=0.000176 Key B never saw key A's limit. There's no second localRateLimit entry for it, no restart to pick up a new key. Any CEL expression over the request works as the bucket key, so this generalizes past API keys to things like a JWT claim or a source IP. One run of the demo hit a transient upstream failure partway through: http.status=503 error="upstream call failed: SendRequest: connection error: peer closed connection without sending TLS close notify" reason=UpstreamFailure x-ratelimit-remaining still dropped on that request. The call never reached Anthropic successfully, a 503 is the opposite of a billable response, but it still counted as one of the 3 admitted requests in the bucket. localRateLimit counts requests agentgateway admits, not requests that succeed upstream. If you're sizing maxTokens close to real traffic, budget headroom for upstream flakiness, because a bad backend day eats your quota exactly like a good one. AgentgatewayModel CRD, now on by default in the Helm chart, and K8s-native session affinity are cluster-side features this standalone run doesn't exercise. remoteRateLimit is a different policy, for quota shared across replicas. localRateLimit buckets live in the single proxy instance that created them, which is exactly what makes this demo's single-container setup representative of the behavior. Requirements: Docker and an ANTHROPIC API KEY . Tested on macOS Apple silicon against cr.agentgateway.dev/agentgateway:v1.6.0 . git clone https://github.com/themsquared/agw-16-hands-on.git cd agw-16-hands-on export ANTHROPIC API KEY=sk-ant-... ./run-demo.sh To check the config against the v1.6.0 schema without sending any traffic: docker run --rm -v "$PWD/config/config.yaml:/config/config.yaml:ro" \ -e ANTHROPIC API KEY=dummy-for-validate \ cr.agentgateway.dev/agentgateway:v1.6.0 -f /config/config.yaml --validate-only Tear down with docker rm -f agw16-demo . Going from v1.5.0 to v1.6.0, the same cost-and-quota problem from the per-key budgets post https://webofmike.com/agentgateway-per-key-llm-budgets/ now needs less from you: no catalog to maintain, and a quota rule that keys itself by request content instead of being written once per key. The gotcha is the same shape either version: a limiter counts what it admits, not what succeeds, and that is worth checking against your own traffic patterns before you pick a maxTokens value. Repo and full captured output: themsquared/agw-16-hands-on https://github.com/themsquared/agw-16-hands-on . Does agentgateway v1.6.0 need a model catalog configured for cost tracking? No. v1.6.0 ships a built-in model catalog, so a route to a known model like claude-sonnet-5 produces llm.cost.total and the input/output cost rates automatically, with no modelCatalog block anywhere in the config. Earlier versions required declaring rates by hand for every model in use. How does agentgateway's per-key CEL rate limiting work? A single localRateLimit policy keyed on an expression like request.headers \ Does a failed upstream request still count against an agentgateway rate limit bucket? Yes. A request that fails upstream, such as a dropped TLS connection, still consumes a token from the bucket. localRateLimit counts requests admitted at the gateway, not successful upstream responses, so a flaky backend can eat into a tight per-key quota without a single call completing. Is agentgateway's remoteRateLimit the same as localRateLimit? No. localRateLimit buckets live in memory on the single gateway instance that created them, which is exactly the single-container setup this demo runs. remoteRateLimit is a separate policy that shares one quota across replicas, which matters once more than one gateway instance sits behind a load balancer and you need one limit enforced across all of them. Canonical version, with machine-readable markdown at https://webofmike.com/agentgateway-v16-cost-tracking/index.md : https://webofmike.com/agentgateway-v16-cost-tracking/ https://webofmike.com/agentgateway-v16-cost-tracking/