Laya

ConvAI Innovationsconvaiinnovations/laya

A fast GPU-backed policy model that turns application state into typed choices, scores, and yes-or-no decisions.

2 providers online

Modality: Decisions
Input: $0.00729; per M tokens
Output: $0.00729; per M tokens
Listed: Sep 22, 2026
Uptime: 100%; last 3 days, measured

Pricing

Charged per use against a signed receipt. Current price version v2; versions are immutable, so the chart below is the platform's actual pricing record.

Input: $0.00729; per M tokens
Output: $0.00729; per M tokens

Trust & routing

Current trust properties and dispatch capacity advertised by the OpenMayhem network.

Registered tiers: T4
Live tiers: T4
Quantizations: bf16
Live routes: 2
Live providers: 2
Prompt processing: Provider-visible
Context capacity: 1K

Routing providers

770e3c83…69b29cb9ddae…f317

Activity

What actually ran on the platform, per day over the last 30 days. Settled usage from receipts; nothing synthetic.

Show as table

Day	input tokens	output tokens	Requests
Sep 22	431,075	160,779	136
Sep 21	0	0	0
Sep 20	0	0	0
Sep 19	0	0	0
Sep 18	0	0	0
Sep 17	0	0	0
Sep 16	0	0	0
Sep 15	0	0	0
Sep 14	0	0	0
Sep 13	0	0	0
Sep 12	0	0	0
Sep 11	0	0	0
Sep 10	0	0	0
Sep 9	0	0	0
Sep 8	0	0	0
Sep 7	0	0	0
Sep 6	0	0	0
Sep 5	0	0	0
Sep 4	0	0	0
Sep 3	0	0	0
Sep 2	0	0	0
Sep 1	0	0	0
Aug 31	0	0	0
Aug 30	0	0	0
Aug 29	0	0	0
Aug 28	0	0	0
Aug 27	0	0	0
Aug 26	0	0	0
Aug 25	0	0	0
Aug 24	0	0	0

Performance

Measured from real, settled requests over the last 30 days. No synthetic benchmarks.

Job duration: 8.2 s; median · p95 39 s · 122 requests
Success rate: 89.7%; 136 finished requests, 30 days

This week: 591.9K tokens across 122 requests.

Availability

Provider availability polled every minute by the platform itself, replayed hour by hour.

100%online over the last 3 days

Tracking since Sep 22, 7 PM

3 days ago online down no dataNow

Providers

Who actually served this model, attributed from signed receipts over the last 30 days.

Provider	Requests	Share	Tokens	Avg latency	Last seen
770e3c83…69b2	85	70.2%	469.2K (80.3%)	11 s	Sep 22
9cb9ddae…f317	36	29.8%	115.2K (19.7%)	17 s	Sep 22

Supported parameters

From the network's signed model contract; anything else is rejected before a provider runs.

auto_task_detectioncheckpointemaillanglimitsmodelquestionsshortliststatetasktemperatureuser

Use it

OpenAI-compatible: point an existing SDK at api.openmayhem.ai and use this model ID.

POST /v1/decisionsDECISIONS · mayhem_decisions +

Working request

curl https://api.openmayhem.ai/v1/decisions \
  -H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "convaiinnovations/laya",
  "state": {
    "message": "The checkout failed and I need help now"
  },
  "questions": {
    "intent": {
      "type": "choice",
      "instructions": "What is the request about?",
      "criteria": {
        "support": "support request",
        "other": "another topic"
      }
    },
    "urgent": {
      "type": "noul",
      "instructions": "Is the request urgent?"
    }
  },
  "checkpoint": "english",
  "task": "typed_decisions",
  "lang": "value"
}'

Parameters

Parameter	Required	Type	Default	Allowed values	Limits and shape
`model`	Required	`string`	—	—	—
`questions`	Required	`object`	—	—	{"intent":{"type":"choice","instructions":"What is the request about?","criteria":{"support":"support request","other":"another topic"}},"urgent":{"type":"noul","instructions":"Is the request urgent?"}}
`state`	Required	`string \| object \| array`	—	—	{"message":"The checkout failed and I need help now"}
`auto_task_detection`	Optional	`boolean`	false	—	—
`checkpoint`	Optional	`string`	—	english, multilingual, typed-decisions	—
`email`	Optional	`object`	—	—	JSON object; use the endpoint-specific schema shown in the examples
`lang`	Optional	`string`	—	—	min length 1; max length 128
`limits`	Optional	`object`	—	—	JSON object; use the endpoint-specific schema shown in the examples
`shortlist`	Optional	`object`	—	—	JSON object; use the endpoint-specific schema shown in the examples
`task`	Optional	`string`	—	typed_decisions	—
`temperature`	Optional	`object`	—	—	JSON object; use the endpoint-specific schema shown in the examples
`user`	Optional	`string`	—	—	min length 1; max length 512

Use this model through MCP

These calls use this model’s exact live request contract. First estimate the unchanged request, then pass the returned estimate ID and maximum cost to the paid tool. Read the complete MCP guide.

decideDECISIONS +

Send this object to estimate_request. Review the result, then send the next object to the named paid tool without changing request.

estimate_request · DECISIONS

{
  "endpoint": "DECISIONS",
  "model": "convaiinnovations/laya",
  "request": {
    "state": {
      "message": "The checkout failed and I need help now"
    },
    "questions": {
      "intent": {
        "type": "choice",
        "instructions": "What is the request about?",
        "criteria": {
          "support": "support request",
          "other": "another topic"
        }
      },
      "urgent": {
        "type": "noul",
        "instructions": "Is the request urgent?"
      }
    },
    "checkpoint": "english",
    "task": "typed_decisions",
    "lang": "value"
  }
}

decide

{
  "model": "convaiinnovations/laya",
  "request": {
    "state": {
      "message": "The checkout failed and I need help now"
    },
    "questions": {
      "intent": {
        "type": "choice",
        "instructions": "What is the request about?",
        "criteria": {
          "support": "support request",
          "other": "another topic"
        }
      },
      "urgent": {
        "type": "noul",
        "instructions": "Is the request urgent?"
      }
    },
    "checkpoint": "english",
    "task": "typed_decisions",
    "lang": "value"
  },
  "estimate_id": "<estimate_id from estimate_request>",
  "max_cost_usd": "<maximum_cost_usd from estimate_request>"
}

Agent drop-ins

This is a media endpoint, so it cannot replace the text model that drives a coding agent. Call the request above from the agent’s HTTP or tool layer.

Create an account →Read the quickstart →

FAQ

What does Laya cost on OpenMayhem?

Laya currently costs $0.00729 / M input · $0.00729 / M output. There is no subscription: you buy credit and every request settles against a signed receipt for exactly what it used. Prices are versioned, and the full price history is published on this page.

Is Laya available right now?

Yes. 2 providers serving Laya right now, and it was online 100% of the last 3 days as measured by our own polling.

How do I use Laya?

Send an OpenAI-compatible request to https://api.openmayhem.ai/v1/decisions with "model": "convaiinnovations/laya" and your API key. Existing OpenAI SDKs work by changing the base URL. Create an account to get a key and starting credit.

Who serves Laya?

Independent providers on the OpenMayhem network run the model on their own hardware. Over the last 30 days, 2 providers served it; the providers table on this page is attributed from signed receipts, not self-reporting.

Are my prompts stored?

OpenMayhem does not persist prompt or completion text. Requests are proxied to the serving provider and only billing metadata is retained: usage counts, the price applied, and the provider's signed receipt. Generated media files are stored temporarily so you can download them, then expire. The provider that serves a request necessarily processes its content.