EvalRouter CLI and Python client

Evaluate models in a full-screen terminal workspace or from scripts. Browse benchmarks, choose models, optionally set a spending cap, follow runs, and compare or export their results. The same package includes the typed Python client, optional trace capture, and benchmark authoring tools.

Requires Python 3.12 or 3.13. Distributed under the proprietary Kimpton EvalRouter SDK License, included as LICENSE in the package.

Install and create your account

We recommend uv to install the CLI in its own Python environment:

uv tool install evalrouter
evalrouter

With pip, use python -m pip install evalrouter in a Python 3.12 or 3.13 environment. uv selects a compatible Python for the CLI and downloads one if needed. If your shell cannot find evalrouter, run uv tool update-shell and restart your terminal. Upgrade an existing installation with evalrouter upgrade (or evalrouter --upgrade). Stable installations stay on stable unless you pass --pre; installed prereleases include prereleases automatically. The command uses uv, pipx or pip in the current virtual environment. Source installs, system Python and installer-pinned versions need their original installer. Check the installed version with evalrouter --version. Use evalrouter --help for explicit commands, or see the CLI guide.

The interactive workspace checks for newer releases in the background and shows an update notice when one is available. The check never installs an update or delays opening the workspace. Set EVALROUTER_NO_UPDATE_CHECK=1 to disable it. Scripts, editable installs and explicitly pinned installations skip update checks.

Complete command names with Tab

For zsh, add this line to ~/.zshrc after your compinit setup, then start a new terminal:

eval "$(evalrouter completion zsh)"

For bash, add this line to ~/.bashrc:

eval "$(evalrouter completion bash)"

Type evalrouter ru and press Tab to complete run. With evalrouter r, Tab shows matching commands such as run, resume and results. The shell setup only completes top-level command names and makes no API request. It does not change interactive prompts or run an evaluation.

This package was previously published as kimpton-evalrouter-sdk. The command stays evalrouter. Use from evalrouter import Client for new integrations; legacy kimpton_evalrouter imports remain compatible and refer to the same public classes. To switch, run uv tool uninstall kimpton-evalrouter-sdk (or pip uninstall -y kimpton-evalrouter-sdk evalrouter) and install evalrouter.

The package supplies the evalrouter command; no repository checkout is needed. Create an EvalRouter account, verify your email, and follow the browser sign-in below. Package installation does not grant account access or evaluation credit.

Sign in with your account:

evalrouter login
evalrouter whoami

Follow the browser sign-in; on a local computer the browser returns to the waiting CLI. For a remote terminal, use evalrouter login --no-browser and approve the code on a device with a browser. New accounts finish setup there. The CLI selects your only workspace automatically, or lets you choose one. Production is the default API; evalrouter options lists --base-url and the other settings that apply to every command. No API key or credential-storage setup is needed for a normal sign-in. The optional evalrouter[keyring] extra enables a compatible OS keychain backend; otherwise credentials use a private file readable only by your user. In the workspace, Account and workspace → Sign in starts the same flow. See the sign-in guide for workspace switching, stored API keys and signing out.

CI and services can use EVALROUTER_API_KEY and EVALROUTER_WORKSPACE_ID supplied privately by a secret manager. Never put credentials in arguments, URLs, request files or logs.

Interactive workspace

Run evalrouter without arguments in a terminal to open the full-screen workspace. Choose Account and workspace → Sign in to connect your account. Local sign-in returns from the browser to the waiting CLI; for a remote terminal, use evalrouter login --no-browser and approve the code on a device with a browser.

Run a benchmark guides you through the benchmark, one to eight models, each model's reasoning settings and coverage. Type to filter lists; Space or Enter toggles a model and Tab continues. A supported native one-model evaluation starts directly with the optional --max-cost cap or available wallet credit, limited by the service maximum. Supported native separate multi-model groups also start directly, with an optional aggregate cap. Their finite service bounds do not reserve the wallet once per model: mandatory fees and live calls use shared available credit. Supported native matched comparisons also start directly with an optional cap; unsupported execution paths retain their quote and cap requirements.

Choose a suggested sample, Custom sample size, or Full benchmark for coverage. A custom sample accepts 1 to 1,000 tasks, limited to the benchmark's task count when known. Full benchmark includes every task.

Home includes Run history, Run groups, and Results, plus model and benchmark browsing, billing and account settings. Results offers Single run, Group run, then Compare runs. Group status shows each model's state; open a member run, return to its group, or keep watching live progress. While watching, choose Open live run in browser or Open live group in browser with Enter, B or a click. Live status continues in the terminal.

Escape goes back; Left also goes back when you are not editing text. Leaving a live run stops watching only: submitted server work continues. Ctrl+Q exits. Use PgUp/PgDn for long reviews and results, and F1 for keyboard help. Select output with the mouse and press Ctrl+C to copy; with no selection, Ctrl+C goes back. Password fields cannot be copied. EVALROUTER_TUI=off selects the older interactive shell; explicit commands, plain output and JSON remain available.

Run a model benchmark

Sign in, choose a ready benchmark and compatible model, then run:

evalrouter login
evalrouter catalog
evalrouter catalog --models
evalrouter run BENCHMARK_SLUG --model MODEL_ID --sample 3

Supported native single-model benchmarks start directly. A spending cap is optional; use --max-cost USD to set one. Without a cap, the service bounds admission using your available wallet credit and its service maximum. An explicit cap is never silently raised. Supported native separate groups and matched comparisons also accept an optional aggregate cap. Other execution paths retain their compatibility, funding and quote requirements.

For scripts, approve paid work explicitly and retain the operation identity:

evalrouter run BENCHMARK_SLUG --model MODEL_ID --sample 3 --yes --json
evalrouter status
evalrouter wait RUN_ID
evalrouter results RUN_ID
evalrouter export RUN_ID --format json --output result.json

A sample is not a full-benchmark score. A local timeout or interrupted watcher does not stop server work. Reuse the saved request identity when recovering an uncertain submission; a new identity can start another evaluation.

Use evalrouter --help and each command's --help for supported options. Account commands include login, whoami, workspace and logout; credits reads balance and holds. Payments take place on the website.

Author your own benchmark

benchmark init, benchmark validate and benchmark bundle run entirely on your machine: no account, no network request, and nothing from your package is imported or executed. The normative validator ships inside evalrouter, and its one dependency (pydantic) is an optional extra. The base installation uses httpx, Rich and Textual. With pip, use pip install 'evalrouter[benchmark]':

uv tool install "evalrouter[benchmark]"
evalrouter benchmark init ./my-benchmark --namespace example --name my-benchmark
evalrouter benchmark validate ./my-benchmark
evalrouter benchmark bundle ./my-benchmark   # evalrouter-bundle-example-my-benchmark-<version>.zip

Without the extra these three commands stop before reading your package and report benchmark_extra_required with the exact install string; --help and every network command keep working. init writes an explicitly synthetic draft and claims no license: replace the tasks, rights, references and limits before submitting. Local validation is not platform admission — EvalRouter revalidates every submission on its own servers.

Where private benchmark imports are enabled, benchmark upload, import and create use workspace-private data with the service's built-in graders. These are account-backed operations, separate from local package validation. See the private benchmark guide for manifests, supported formats, source management and permissions.

Python client

Install with python -m pip install evalrouter in your application's environment. The import name is evalrouter; the client supports context-manager cleanup:

Canonical imports require a release containing this namespace. Older registry releases through 0.3.24 use kimpton_evalrouter. Current releases provide the canonical evalrouter import.

import os
from evalrouter import Client

with Client(
    base_url="https://api.evalrouter.ai",
    api_key=os.environ["EVALROUTER_API_KEY"],
    workspace_id=os.environ["EVALROUTER_WORKSPACE_ID"],
) as client:
    print(client.catalog.models())

Use client.catalog, client.evals, client.quotes and client.runs for typed discovery, submission and result resources. Creating a quote starts no evaluation; submitting its accepted ID can start paid work. Keep the quote ID and idempotency key before submission. The model API guide describes request fields, limits and result contracts.

Import LangSmith traces

The optional langsmith extra provides a local connector for completed agent runs. Where your workspace has Traces, create an SDK destination connection in Traces → Connect agent, then supply LANGSMITH_API_KEY and the connection's EvalRouter environment variables through your secret manager. The source key is never sent to EvalRouter.

python -m pip install 'evalrouter[langsmith]'
python -m evalrouter.langsmith projects
python -m evalrouter.langsmith sync --project 'YOUR_PROJECT_ID' \
  --state './.private/evalrouter-langsmith-state.json' --metadata-only --watch

The process must stay running for automatic imports. Its private checkpoint resumes progress across restarts. Set --since to an ISO timestamp to choose the initial import window. This explicit metadata-only mode omits source names, inputs, outputs, error text, tags, events and arbitrary metadata. Hierarchy, timing, error status and reported numeric usage remain. The compatibility default captures bounded field-name-redacted content if --metadata-only is omitted.

Checkpoint version 2 binds the content policy and destination. Unknown acknowledgments replay a private adjacent .delivery.json payload unchanged; keep it with the checkpoint. A policy change on an existing checkpoint is refused. Version 1 upgrades only in its original content-capture mode and cannot restore payload bytes lost by the older connector. Finish unresolved deliveries before using a new checkpoint and connection for a different policy. Only activity recorded by LangSmith can be imported; two stable closed reads are observed coverage, not proof that every upstream child exists.

Live agent capture

Install with python -m pip install 'evalrouter[tracing]' in your agent's own environment. Configure EVALROUTER_BASE_URL, EVALROUTER_WORKSPACE_ID, EVALROUTER_TRACE_CONNECTION_ID and the restricted EVALROUTER_TRACE_KEY through an authorized secret manager. Package installation and connection authorization are separate.

import json
import os
from anthropic import Anthropic
from evalrouter.tracing import TraceCapture

# Also install anthropic, and supply ANTHROPIC_API_KEY privately.
model = Anthropic(max_retries=0)
capture = TraceCapture(capture_content=True)
with capture.agent("Support assistant") as root:
    root.input({"message": "Explain what an evaluation benchmark is."})
    with capture.model(os.environ["ANTHROPIC_MODEL"]) as span:
        answer = model.messages.create(
            model=os.environ["ANTHROPIC_MODEL"], max_tokens=256,
            messages=[{"role": "user", "content": "Explain what an evaluation benchmark is."}],
        )
        text = "".join(block.text for block in answer.content if block.type == "text")
        span.output({"answer": text})
    root.output({"answer": text})
receipt = capture.seal(root.trace_id)
print(json.dumps(receipt))
if receipt["state"] != "accepted" or not receipt["complete"] or not capture.close():
    raise SystemExit(1)

This example makes a real paid model request. Content capture is explicitly enabled; use capture_content=False to omit input, output and error payloads. Caller attributes still require your metadata policy. Common secret field names are redacted, but secrets in arbitrary text cannot be detected. Content capture defaults to true; select metadata-only explicitly.

Root exit and flush() do not seal. Join owned children, then seal(root.trace_id) to acknowledge closure. receipt(root.trace_id) reports local delivery state, counts, accepted server UUID and server completion, independently of evaluation completion. Unknown acknowledgments retain identical batches for later flush/seal/close on the same instance. Zero newly inserted spans on replay is success. close() returns false while active, failed or unknown, and true after acknowledged closure and shutdown. A context manager calls close, but does not raise on a false result; inspect receipts explicitly. There is no background HTTP export. Buffers are process-local; retry before exit. Each instance retains at most 64 local trace receipts, 512 active spans and 16 MiB of pending records. When another root needs room, the oldest successfully sealed idle receipt is evicted. Save the receipt/server UUID if you need it later; receipt(id) raises ValueError after eviction. Pending, unknown, active or dropped traces are never evicted. If all 64 are unsettled, a new root is not recorded (its handle has no trace ID and failed_exports increases); resolve delivery or use another instance. Late activity inherited from an evicted trace is rejected, never made a new root. Close attempts every retained trace within one aggregate deadline and leaves the provider alive if any closure fails. Capture loss prevents successful seal. The optional OpenTelemetry dependency stays isolated from the base HTTP client.

Create a connection under Traces → Connect agent where Traces is enabled for your workspace. Detailed delivery receipts are described in the trace connection setup in your workspace.

Attach existing OpenTelemetry instrumentation

Install the evalrouter[tracing] extra into your existing Python 3.12/3.13 agent environment. Pass the OTel SDK provider the framework actually uses; do not replace its global provider. No agent inheritance or per-call EvalRouter wrappers are required for supported spans:

from evalrouter.tracing import TraceCapture

capture = TraceCapture(capture_content=False)
attachment = capture.attach(existing_provider, scope_names=("your.instrumentation",))
# Run the already-instrumented agent, then join all owned child work.
for trace_id in attachment.trace_ids:
    receipt = capture.seal(trace_id)
    print(receipt)  # IDs/counts/delivery state only; inspect accepted + complete.
# At application shutdown, check capture.close(); it never stops existing_provider.

Attachment exports metadata only, even when wrapper content capture is enabled. It removes source names, resource attributes, events, prompts, tool arguments, results and exception text. It retains original trace/span/parent IDs, closed operation/kind/status enums and bounded numeric token counters. Source counters are observations, not native usage charges. evalrouter.otel.status=unset means unknown source success: wire ok only means no explicit source ERROR, never a native grade or proof that a tool succeeded. Unknown/conflicting kinds are counted in attachment.unsupported_spans and prevent successful sealing. Provider flush queues records; it does not prove accepted ingestion or closure.

The optional [strands] extra pins Strands for applications that need it; the base client has no Strands dependency. Attachment only sees selected spans that the supplied provider actually records. It cannot recover unsampled or missing work, or capture uninstrumented frameworks automatically. LangSmith project imports and ACP evaluation execution are separate integrations.

Native multi-model client requests

Supported native separate groups and matched comparisons start directly with an optional aggregate spending cap. Other execution paths retain their quote and cap requirements. Hosted route availability is checked by the service.

from evalrouter import Client

with Client() as client:
    group = client.run_groups.create({
        "models": [
            {"kind": "managed", "route_id": "YOUR_FIRST_ROUTE"},
            {"kind": "managed", "route_id": "YOUR_SECOND_ROUTE"},
        ],
        "selection": {"profile_ids": ["YOUR_EXACT_NATIVE_PROFILE"]},
        "coverage": {"mode": "sample", "sample_count": 1, "seed": 42},
        # Optional aggregate stop limit, in integer micro-USD:
        # "max_charge_microusd": "2000000",
    }, idempotency_key="persist-this-group-request-key")
    # If work stops, resume eligible native member chains with a NEW durable key:
    # continued = client.run_groups.resume(group["id"], {},
    #     idempotency_key="persist-this-continuation-request-key")

An omitted customer cap returns max_charge_microusd=None; authorization_limit_microusd is a finite service bound. It is not the money reserved or a budget selected by you. Preserve the exact body and key across uncertain replies. Actual charges and available wallet credit remain authoritative.