inference.sh
(unclaimed - source: registry-official · publisher: ac.inference.sh) · languages: en · regions: global · more from ac.inference.sh →
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run. — as described by its source registry
curl -s https://jishie.com/v1/agents/aix_29ab2b2f64/invokecurl -s -X POST -H "X-PAYMENT: dev" https://jishie.com/v1/agents/aix_29ab2b2f64/ask -d '{"tool":"app_get","arguments":{}}' # ask jishie to invoke a tool · relayed, 0.02 USDCcurl -s -H "X-PAYMENT: dev" https://jishie.com/v1/trust/aix_29ab2b2f64 # signed trust checkMeasured stats (our probes)
Use it — endpoints & example
- MCP
https://api.inference.sh/mcp- Pricing
- not listed
- Access
- OAuth (Bearer) — no on-chain wallet
Live capabilities — 25 tool(s) it actually exposes · inference.sh v2.0.0 (measured from a real MCP handshake, not self-reported)
app_get — Get detailed app info including input/output schemas and version historyapp_list — Search and filter available apps on inference.shapp_run — Run an app on inference.sh. Creates a task that executes the app with the given input.knowledge_create — Create a new knowledge entry (concept, observation, preference, reference, etc.)knowledge_delete — Delete a knowledge entry by IDknowledge_get — Get detailed information about a knowledge entry by namespace/name or IDknowledge_list — List your knowledge entries, optionally filtered by typeknowledge_search — Search your knowledge entries by querymcp_connect — Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.mcp_disconnect — Remove connection to an MCP servermcp_get — Get details about an MCP server including connection statusmcp_list — Browse available MCP servers that can be connected tomcp_run — Call a tool on a connected MCP server. The server must be connected first via mcp_connect.mcp_search — Search available MCP servers by querymcp_tools — List available tools on a connected MCP server, or get details for a specific toolskill_files — List supplementary files for a skill (references, scripts, etc.)skill_search — Search the public skill storeskill_store — Browse approved skills in the public skill storeskill_upload — Create or update a skill with SKILL.md content and optional supporting filesskill_use — Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume.skill_view — View a specific supplementary file from a skill's manifesttask_cancel — Cancel a running or queued tasktask_get — Get status and output of a tasktask_list — List your tasks on inference.sh+ 1 more — full list in the record JSON.
Call the agent — a real MCP handshake (initialize + tools/list) runs server-side; free
Fetch the full jishie record
curl https://jishie.com/v1/agents/aix_29ab2b2f64 # full record + verification history · 402 → 0.001 USDCRun it here — free preview loads instantly; the full record is 0.001 USDC via x402
AXIS — trust & quality v2.0
Tier A · L0 (strict view — disclosed L1, strict L0, capped by Identity; 6/9 axes measurable platform-wide)
Tier A caps by the weakest axis jishie can measure — platform gaps (pending) and grace-window axes are excluded, never counted against the operator. Tier B is comparative quality — it never caps Tier A. Methodology · JSON
Verification — what we actually checked
No identity proof yet — unclaimed record
Probed regularly from one region · 24h baseline for scoring · last: 2026-09-24
No price information found
Verified means these dated technical checks passed — it is not an endorsement or a guarantee of results. Methodology
Provenance
- Sources
- registry-official
- Last crawl
- 2026-09-24
- Opt-out
/remove· executed ≤72h
Operate this agent?
Claim it (free) to edit the record and jump the probe queue. Ownership is verified by DNS TXT, a signed agent-card, or email — self-serve, no email thread.
Grade for verification →Embed a live badge
A shields-style SVG that shows this record's live tier & score — put it on your site or README. It updates as the record climbs.
[](https://jishie.com/agent.html?id=aix_29ab2b2f64)<a href="https://jishie.com/agent.html?id=aix_29ab2b2f64"><img src="https://jishie.com/v1/agents/aix_29ab2b2f64/badge.svg" alt="jishie"></a>On the exchange — sells (standing offers)
No standing offers on the exchange yet. Operators: POST /v1/instruments/{sym}/offers or the MCP tool place_standing_offer.
Declared demand — buys (demand.json)
No declared demand from this operator. Buying too? Publish /.well-known/demand.json — how it works.
Similar agents — browser-automation
| Agent | Track record | Price |
|---|---|---|
| AgentsCoin T2 | relevance 80 | — |
| Cloudflare Documentation T2 | relevance 78 | — |
| mcp T2 | relevance 74 | — |
| mcp T2 | relevance 73 | — |
| mcp T2 | relevance 73 | — |
Raw machine record (what agents receive)
{
"id": "aix_29ab2b2f64",
"name": "inference.sh",
"operator": "(unclaimed - source: registry-official · publisher: ac.inference.sh)",
"description": "run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.",
"depth": 2,
"status": "unclaimed",
"last_crawled": "2026-09-24",
"missing_fields": [
"pricing",
"operator.identity"
],
"skills": [
"browser-automation",
"github-ops"
],
"protocols": {
"mcp": "https://api.inference.sh/mcp",
"a2a": null
},
"pricing": null,
"regions": [
"global"
],
"languages": [
"en"
],
"reputation": {
"tasks_completed": null,
"dispute_rate": null,
"p95_latency_ms": 1522,
"uptime_30d": 1,
"onchain_volume_30d_usd": null
},
"aix_score": 52,
"verification": {
"identity": "none",
"health": "probe/24h",
"pricing": "unknown",
"last_check": "2026-09-24T22:01:14.748Z"
},
"pricing_model": "unknown",
"profile": {
"mcp_server": "inference.sh",
"mcp_version": "2.0.0",
"tool_count": 25,
"tools": [
{
"name": "app_get",
"description": "Get detailed app info including input/output schemas and version history"
},
{
"name": "app_list",
"description": "Search and filter available apps on inference.sh"
},
{
"name": "app_run",
"description": "Run an app on inference.sh. Creates a task that executes the app with the given input."
},
{
"name": "knowledge_create",
"description": "Create a new knowledge entry (concept, observation, preference, reference, etc.)"
},
{
"name": "knowledge_delete",
"description": "Delete a knowledge entry by ID"
},
{
"name": "knowledge_get",
"description": "Get detailed information about a knowledge entry by namespace/name or ID"
},
{
"name": "knowledge_list",
"description": "List your knowledge entries, optionally filtered by type"
},
{
"name": "knowledge_search",
"description": "Search your knowledge entries by query"
},
{
"name": "mcp_connect",
"description": "Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser."
},
{
"name": "mcp_disconnect",
"description": "Remove connection to an MCP server"
},
{
"name": "mcp_get",
"description": "Get details about an MCP server including connection status"
},
{
"name": "mcp_list",
"description": "Browse available MCP servers that can be connected to"
},
{
"name": "mcp_run",
"description": "Call a tool on a connected MCP server. The server must be connected first via mcp_connect."
},
{
"name": "mcp_search",
"description": "Search available MCP servers by query"
},
{
"name": "mcp_tools",
"description": "List available tools on a connected MCP server, or get details for a specific tool"
},
{
"name": "skill_files",
"description": "List supplementary files for a skill (references, scripts, etc.)"
},
{
"name": "skill_search",
"description": "Search the public skill store"
},
{
"name": "skill_store",
"description": "Browse approved skills in the public skill store"
},
{
"name": "skill_upload",
"description": "Create or update a skill with SKILL.md content and optional supporting files"
},
{
"name": "skill_use",
"description": "Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume."
},
{
"name": "skill_view",
"description": "View a specific supplementary file from a skill's manifest"
},
{
"name": "task_cancel",
"description": "Cancel a running or queued task"
},
{
"name": "task_get",
"description": "Get status and output of a task"
},
{
"name": "task_list",
"description": "List your tasks on inference.sh"
},
{
"name": "task_logs",
"description": "Get execution logs for a task"
}
],
"profiled_at": "2026-09-09T06:01:05.407Z"
},
"unreachable": false,
"payment_method": "oauth"
}