TensorMesh

TensorMesh API

TensorMesh API as documented publicly: 11 operations. Contract generated from the documentation by API Evangelist (2026-10-19); not the provider's own document.

Documentation GitHub OpenAPI

Operations 11

GET / GET / #

GET /api/v1/label/__name__/values Operations Metrics #

GET /api/v1/query GET /api/v1/query #

GET /api/v1/series Operations Metrics #

GET /health GET /health #

GET /install-cli.sh GET /install-cli.sh #

GET /l2/backends GET /l2/backends #

GET /metrics GET /metrics #

GET /v1/chat/completions Integrations NVIDIA Dynamo #

POST /v1/chat/completions POST /v1/chat/completions #

GET /v1/completions GET /v1/completions #

Specifications

⚙

OpenAPI

https://raw.githubusercontent.com/api-evangelist/tensormesh/refs/heads/main/openapi/_ae-authored/tensormesh-openapi-generated.yml

Schemas & Data

📊

JSONSchema

https://raw.githubusercontent.com/api-evangelist/tensormesh/refs/heads/main/json-schema/tensormesh-post-v1-chat-completions-request-schema.json

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/tensormesh:tensormesh-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.1.0
info:
  title: TensorMesh API
  version: '2026-10-19'
  description: 'GENERATED FROM DOCUMENTATION by API Evangelist on 2026-10-19: 11 operation(s) read from 17 public documentation page(s) (each
    operation names its page in x-source). This is not the provider''s published contract; TensorMesh has published no machine-readable contract
    that the pipeline could find. Engine: local.'
  x-evidence-tiers:
    code-example: 8
    documentation: 3
    pages-with-code: 17
    pages-read: 17
  x-generated-from: documentation
  x-provenance: generated
  x-authored-by: API Evangelist
  x-generated: '2026-10-19'
  x-generator: generate-contract-from-docs.py
  x-engine: local
  x-sources:
  - https://docs.tensormesh.ai/v1.0.0/reference/cli.md
  - https://docs.tensormesh.ai/v1.0.1/reference/cli.md
  - https://docs.tensormesh.ai/v1.0.1/reference/cli
  - https://docs.tensormesh.ai/v1.0.1/observability
  - https://docs.tensormesh.ai/v1.0.0/observability.md
  - https://docs.tensormesh.ai/v1.0.1/observability.md
  - https://docs.tensormesh.ai/v1.0.1/configuration/p2p
  - https://docs.tensormesh.ai/v1.0.1/integrations/dynamo
  - https://docs.tensormesh.ai/v1.0.0/configuration/p2p.md
  - https://docs.tensormesh.ai/v1.0.1/configuration/p2p.md
  - https://docs.tensormesh.ai/v1.0.1/installation/example
  - https://docs.tensormesh.ai/v1.0.1/observability/metrics
  - https://docs.tensormesh.ai/v1.0.0/integrations/dynamo.md
  - https://docs.tensormesh.ai/v1.0.1/integrations/dynamo.md
  - https://docs.tensormesh.ai/v1.0.0/installation/example.md
  - https://docs.tensormesh.ai/v1.0.1/installation/example.md
  - https://docs.tensormesh.ai/v1.0.0/observability/metrics.md
servers:
- url: https://operator.tensormesh.ai
paths:
  /:
    get:
      operationId: get
      tags:
      - Api
      summary: GET /
      x-source: https://docs.tensormesh.ai/v1.0.1/observability/metrics
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -s ''http://<prometheus>/api/v1/label/__name__/values''  | jq -r ''.data[] | select(startswith("lmcache_mp_"))'' '
  /api/v1/label/__name__/values:
    get:
      operationId: get_api_v1_label_name_values
      tags:
      - Api
      summary: Operations Metrics
      x-source: https://docs.tensormesh.ai/v1.0.1/observability/metrics
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: documentation
  /api/v1/query:
    get:
      operationId: get_api_v1_query
      tags:
      - Api
      summary: GET /api/v1/query
      x-source: https://docs.tensormesh.ai/v1.0.1/observability/metrics
      parameters:
      - name: query
        in: query
        required: false
        schema:
          type: string
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl -s 'http://localhost:9091/api/v1/query?query=sum(rate(lmcache_mp_lookup_hit_tokens_total[5m]))/sum(rate(lmcache_mp_lookup_requested_tokens_total[5m]))'\
          \  | jq -r '.data.result[0].value[1]' \n A batch of lmcache_mp_* lines (or a number from the query) confirms metrics are flowing. Empty\n\
          means no traffic has hit the engine yet; send some inference through vLLM first. \n  Pull every metric \n See t"
  /api/v1/series:
    get:
      operationId: get_api_v1_series
      tags:
      - Api
      summary: Operations Metrics
      x-source: https://docs.tensormesh.ai/v1.0.1/observability/metrics
      parameters:
      - name: match[]
        in: query
        required: true
        schema:
          type: string
        description: Series selector to match
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: documentation
  /health:
    get:
      operationId: get_health
      tags:
      - Health
      summary: GET /health
      x-source: https://docs.tensormesh.ai/v1.0.1/integrations/dynamo
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl --silent --fail http://localhost:8000/health > /dev/null ; do \n sleep 2 \n done "
  /install-cli.sh:
    get:
      operationId: get_install_cli_sh
      tags:
      - Install Cli
      summary: GET /install-cli.sh
      x-source: https://docs.tensormesh.ai/v1.0.0/reference/cli.md
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -sSfL https://operator.tensormesh.ai/install-cli.sh | TMO_TOKEN=<TOKEN_FROM_TENSORMESH> sh

          ```'
  /l2/backends:
    get:
      operationId: get_l2_backends
      tags:
      - L2
      summary: GET /l2/backends
      x-source: https://docs.tensormesh.ai/v1.0.1/configuration/p2p
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl -s http://localhost:48080/l2/backends | jq . \n The L2 backends endpoint and its response format may change in future releases.\
          \ This section\nwill be updated as the API stabilizes. \n  Common mistakes \n Forgetting to move server.port and server.httpPort to\
          \ high ports when using hostNetwork ,\ncausing bind failures on ports already in use by the host \n Not setting engine.p2p.enabled:\
          \ true — hostN"
  /metrics:
    get:
      operationId: get_metrics
      tags:
      - Metrics
      summary: GET /metrics
      x-source: https://docs.tensormesh.ai/v1.0.1/observability
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -s http://localhost:8889/metrics | grep lmcache | head -20 '
  /v1/chat/completions:
    get:
      operationId: get_v1_chat_completions
      tags:
      - Chat
      summary: Integrations NVIDIA Dynamo
      x-source: https://docs.tensormesh.ai/v1.0.1/integrations/dynamo
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: documentation
    post:
      operationId: post_v1_chat_completions
      tags:
      - Chat
      summary: POST /v1/chat/completions
      x-source: https://docs.tensormesh.ai/v1.0.1/integrations/dynamo
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostV1ChatCompletionsRequest'
      responses:
        '201':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl --silent --show-error http://localhost:8000/v1/chat/completions  --header \"Content-Type: application/json\"  --data '{\
          \ \n \"model\": \"Qwen/Qwen3-0.6B\", \n \"messages\": [ \n {\"role\": \"user\", \"content\": \"What is NVIDIA Dynamo?\"} \n ], \n \"\
          max_tokens\": 200 \n }' \n  Verify the cache is working \n Send the same long prompt twice (it must exceed the engine’s chunk_size\
          \ — 256 tokens\nby default — or nothing is"
  /v1/completions:
    get:
      operationId: get_v1_completions
      tags:
      - Completions
      summary: GET /v1/completions
      x-source: https://docs.tensormesh.ai/v1.0.1/installation/example
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -sS http://localhost:8000/v1/completions  -H ''Content-Type: application/json'' -d " $PAYLOAD " | jq -r ''.choices[0].text'' '
components:
  schemas:
    PostV1ChatCompletionsRequest:
      type: object
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
        max_tokens:
          type: integer
tags:
- name: Api
- name: Chat
- name: Completions
- name: Health
- name: Install Cli
- name: L2
- name: Metrics