Models

Keiro currently exposes four public paid-beta eb1 model IDs. If you are unsure which to use, start with eb1-preview and change only after measuring your workload.

On this page 1 of 6

Choose a public eb1 model

Keiro Étude is the first generation of eb1. The next is already in training.

eb1-frontier-preview Highest quality 400,000 ctx · $10.00 / $50.00 / 1M tokens input / output eb1-preview Default Recommended default 400,000 ctx · $2.00 / $12.00 / 1M tokens input / output eb1-efficient-preview Lower cost 400,000 ctx · $1.25 / $7.50 / 1M tokens input / output eb1-fast-preview Lower latency 240,000 ctx · $0.80 / $5.00 / 1M tokens input / output

Public models#

Model	Choose it for	Tradeoff
`eb1-preview`	General reasoning, coding, and application work	Recommended balanced default
`eb1-frontier-preview`	The hardest reasoning and synthesis workloads	Prioritizes capability over latency and spend
`eb1-fast-preview`	Interactive and latency-sensitive requests	Prioritizes speed over maximum quality
`eb1-efficient-preview`	Repeated routine work and cost-aware throughput	Prioritizes efficiency and predictable spend

These strings are executable API identifiers, not descriptions of private serving routes. Do not derive or invent other model names from them.

List available models#

Model availability is account- and key-scoped:

Run a curl request Shell

printf 'Keiro API key: '
IFS= read -rs KEIRO_BEARER
printf '\n'

curl -sS https://api.keirolabs.ai/v1/models \
  -H @- <<<"Authorization: Bearer $KEIRO_BEARER" | python3 -m json.tool

Use only IDs returned for the key. Authenticated OpenAI-style model entries can include rate_limits; those are configured Keiro limits for the requesting account and API key, not upstream provider quotas or live route capacity.

Select by measurement#

Evaluate the same representative prompts against the public models you are considering. Compare output quality, end-to-end latency, token usage, and billable amount in the console. Keep safety checks and tool/image workflows in the evaluation; text-only prompts do not prove capability parity for an agentic application.

Pin the chosen public ID in production configuration. A silent fallback to a different ID hides access and compatibility errors.

Missing access or capability#

If an expected model is missing, check the selected console organization and the key's restrictions, then contact support. If an image or tool request fails with a capability error, select another account-enabled public model or ask support to confirm the contract. Do not remove required input silently.