Convai: Laya
convaiinnovations/layaHugging FaceDecisionscalibrated-decisionsclassificationguardrailslayamoderationreinforcement-learningrlcdroutingscoringsystem-onetext-classification
Providers
Live endpoints for this model. Response is the time from request to result; uptime is measured over the last day and week. Nothing here streams, so there is no first token to time and no token rate to report.
| Provider | Context | Input | Response | Capacity | Uptime 1d | Uptime 7d | Health | Data |
|---|---|---|---|---|---|---|---|---|
| ImpCCfp1690% offCA | 512 | $0.0042 | 163ms30m | 1/1 free | 100.0% | 100.0% | Healthy | ZDR |
Pricing
USD per million input tokens.
| Provider | Input |
|---|---|
| ImpCCfp1690% off | $0.0042 |
Price history
Input price · USD per million tokens
Performance
Percentiles cover the labelled window: the last 30 minutes when it has enough samples, otherwise the last day. Response is the time in seconds from request to result. This model answers whole rather than streaming, so there is no first token to time and no rate between tokens to report — response time is the whole measurement there is.
| Provider | Response p50 | p75 | p90 | p99 |
|---|---|---|---|---|
| ImpCCfp16 | 163ms30m | 836ms | 1.45s | 1.45s |
Uptime
Share of successful requests and probes over the last day and week.
- ImpCCfp161d 100.0%7d 100.0%Healthy
Availability by hour · last 7 days
Share of successful requests and probes per hour and provider. The line spans hours with nothing to measure; where samples are sparse, a dot marks each hour actually measured.
Activity
Tokens judged per UTC day over the last 30 days. Every billed request counts, the platform's own paid probe traffic included.
import { TypeSafeClient, choice } from "@typesafe-ai/sdk";const client = new TypeSafeClient({ baseURL: "https://api-staging.heimdallm.com/api", apiKey: process.env.HEIMDALL_API_KEY,});const reply = await client.systemOne({ model: "convaiinnovations/laya", state: "We were billed twice. Please refund the duplicate charge.", questions: { dept: choice("Which team?", { billing: "Invoices and refunds", engineering: "Bugs and outages", }) },});console.log(reply.answers.dept);Set HEIMDALL_API_KEY to a key from your account. See the quickstart for routing suffixes and provider preferences.
About
Multilingual, non-autoregressive System 1 decision model. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with mathematically calibrated probabilities in a single forward pass (33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (RLCD), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate.
- Author
- Convai
- Family
- convaiinnovations/laya
- Weights
- convaiinnovations/laya
- Parameters
- —
- Licence
- apache-2.0
- Size
- 421M parameters, F16 weights
- Tokenizer
- —
- Available until
- —
From the model card
What the repository states about these weights, read from convaiinnovations/laya on Oct 9, 2026.
- Languages
- —
- Papers
- —
- Datasets
- —
- Revision
- 7b928d8Oct 3, 2026
- Downloads
- 41.5K
- Likes
- 5.4K