FreePublished on GitHubEnglish overview

omni-inference

Connect AI agents to OmniRoute for chat, image generation, speech, transcription, web search, and page retrieval. Also generate embeddings, numerical representations used for search, through documented APIs with model discovery and request examples.

OriginalShow the original description

The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.

cheaper-inference/OmniRoute

Works withOpenAI

AI rating70/ 100 See how to install

Good for

Connect an agent to chat and image generation
Add speech output and audio transcription
Generate numerical text representations for search
Integrate web search and page retrieval

Overview

What it does

omni-inference uses OmniRoute APIs to add text generation, image generation, speech generation, and audio transcription to AI agents. It also supports embeddings, which are numerical representations of text used for search and similar tasks, along with web search and page content retrieval. Chat examples cover the OpenAI format, Anthropic Messages format, and OpenAI Responses API. The introduction also explains how to find available models.

When it helps

Use it when you want an agent to call several AI capabilities. Possible uses include receiving an audio transcription in subtitle format, saving generated speech to a file, and retrieving a page as Markdown. You can also use model combinations that try multiple connections in sequence.

Example requests

“Add calls for chat and image generation to my agent.”
“Transcribe this audio file and return the result in subtitle format.”
“Connect web search with page content retrieval.”

Notes

You need to configure OMNIROUTE_URL and OMNIROUTE_KEY. API authentication uses a Bearer token or session cookie. Available image sizes, voice options, input length limits, and file size limits vary by model and provider.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?: AGoodThe overview identifies chat, image, and audio inference APIs and their use in agent integration.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?: BPartly lackingThe supplied excerpt lists API methods and paths but provides no request bodies or response examples.
SafetyAre sending data, deleting files, and running commands disclosed?: BPartly lackingCredential retrieval and deletion APIs are listed, but no confirmation procedure is provided before execution.
Easy setupDoes it need few tools or API keys, and are they documented?: BPartly lackingToken acquisition and authentication methods are documented, but OmniRoute installation instructions are absent.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 22, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Files included (2)

SKILL.md21.5 KB
references/endpoints.md42.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Overview

The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

Chat completions

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoints

POST $OMNIROUTE_URL/v1/chat/completions — OpenAI format
POST $OMNIROUTE_URL/v1/messages — Anthropic Messages format
POST $OMNIROUTE_URL/v1/responses — OpenAI Responses API

Discover

curl $OMNIROUTE_URL/v1/models | jq '.data[].id'

Combos (e.g. auto, cost-optimized, subscription) auto-fallback through multiple providers.

OpenAI format example

curl -X POST $OMNIROUTE_URL/v1/chat/completions \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "messages": [{"role": "user", "content": "Refactor this function"}],
    "stream": true
  }'

Anthropic format example

curl -X POST $OMNIROUTE_URL/v1/messages \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "max_tokens": 4096,
    "messages": [{"role": "user", "content": "Hi"}]
  }'

Tool use

Supports OpenAI tools array and Anthropic tools block. Tool results auto-compressed via RTK (47 filters: git-diff, grep, test-jest, terraform-plan, docker-logs, etc.) — 20-40% token savings. Disable per-request with X-Omniroute-Rtk: off header.

Reasoning / thinking

Anthropic extended thinking and OpenAI Responses reasoning blocks are forwarded verbatim. Cached automatically via reasoning cache.

Errors

401 → invalid API key
400 invalid_model → model not in registry; check /v1/models
503 circuit_open → provider circuit breaker tripped; retry later or use combo
429 rate_limited → honor Retry-After; consider using a combo for auto-fallback

Image generation

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoints

POST $OMNIROUTE_URL/v1/images/generations — Text-to-image
POST $OMNIROUTE_URL/v1/images/edits — Image edit (mask)
POST $OMNIROUTE_URL/v1/images/variations — Variations

Discover

curl $OMNIROUTE_URL/v1/models/image | jq '.data[]'

Returns { id, owned_by, sizes:[...], capabilities:[...] } per model.

Generate example

curl -X POST $OMNIROUTE_URL/v1/images/generations \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "a red bicycle on a wet street, photoreal",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json"
  }'

Response: { created, data: [{ url? or b64_json, revised_prompt }] }

Errors

400 invalid_size → not supported by this model; check /v1/models/image
400 content_policy_violation → blocked by provider safety
503 → provider unavailable; try another model in /v1/models/image

Text-to-speech

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoint

POST $OMNIROUTE_URL/v1/audio/speech — returns binary audio (mp3/opus/wav/flac)

Discover

curl $OMNIROUTE_URL/v1/models/tts | jq '.data[]'

Each entry includes voices:[...] for the available voice names per provider.

Example

curl -X POST $OMNIROUTE_URL/v1/audio/speech \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello from OmniRoute.",
    "voice": "alloy",
    "response_format": "mp3"
  }' --output speech.mp3

Voices

Voice names vary by provider. Check /v1/models/tts — each entry has voices:[...]. Common OpenAI voices: alloy, echo, fable, onyx, nova, shimmer.

Errors

400 invalid_voice → voice not supported by this model
400 input_too_long → input exceeds model character limit
503 → provider unavailable; try another model in /v1/models/tts

Speech-to-text

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoints

POST $OMNIROUTE_URL/v1/audio/transcriptions — multipart upload, returns text
POST $OMNIROUTE_URL/v1/audio/translations — transcribe + translate to English

Discover

curl $OMNIROUTE_URL/v1/models/stt | jq '.data[]'

Example

curl -X POST $OMNIROUTE_URL/v1/audio/transcriptions \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1" \
  -F "response_format=verbose_json"

Response: { text, language, duration, segments?:[{ start, end, text }] }

Supported formats

Audio: mp3, mp4, mpeg, mpga, m4a, wav, webm. Response formats: json, text, srt, verbose_json, vtt.

Errors

400 invalid_file_format → unsupported audio format
400 file_too_large → exceeds provider limit (usually 25MB)
503 → provider unavailable; try another model in /v1/models/stt

Embeddings

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoint

POST $OMNIROUTE_URL/v1/embeddings

Discover

curl $OMNIROUTE_URL/v1/models/embedding | jq '.data[]'

Each entry: { id, owned_by, dimensions, max_input_tokens }.

Example

curl -X POST $OMNIROUTE_URL/v1/embeddings \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": ["first text", "second text"],
    "encoding_format": "float"
  }'

Response: { data:[{ embedding:[...], index }], usage:{ prompt_tokens, total_tokens } }

Batch input

input accepts a string or array of strings (up to provider batch limit, typically 2048 items).

Errors

400 input_too_long → input exceeds max_input_tokens for this model
400 invalid_encoding_format → use float or base64
503 → provider unavailable; try another model in /v1/models/embedding

Web search

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoint

POST $OMNIROUTE_URL/v1/web/search — unified search format

Discover

curl $OMNIROUTE_URL/v1/models/web | jq '.data[] | select(.kind == "webSearch")'

Example

curl -X POST $OMNIROUTE_URL/v1/web/search \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tavily/search",
    "query": "OmniRoute github latest release",
    "max_results": 5,
    "include_answer": true
  }'

Response: { answer?, results:[{ url, title, content, score }] }

Parameters

Field	Type	Description
`model`	string	Provider model from `/v1/models/web`
`query`	string	Search query
`max_results`	number	Max results (default: 5)
`include_answer`	boolean	Include AI-synthesized answer
`search_depth`	string	`basic` or `advanced` (Tavily)

Errors

400 query_too_long → shorten the search query
503 → provider unavailable; try another model in /v1/models/web

Web fetch

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoint

POST $OMNIROUTE_URL/v1/web/fetch

Discover

curl $OMNIROUTE_URL/v1/models/web | jq '.data[] | select(.kind == "webFetch")'

Example

curl -X POST $OMNIROUTE_URL/v1/web/fetch \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina/reader",
    "url": "https://anthropic.com",
    "format": "markdown"
  }'

Response: { url, title, markdown, links?:[...], images?:[...] }

Parameters

Field	Type	Description
`model`	string	Provider from `/v1/models/web` (e.g. `jina/reader`, `firecrawl/scrape`)
`url`	string	URL to fetch
`format`	string	`markdown` (default), `html`, `text`

Errors

400 invalid_url → URL must be http/https
403 blocked → provider blocked by target site; try a different model
503 → provider unavailable; try another model in /v1/models/web

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

More skills from this repository

cli-a2a

FreeSummaryAI rating 90

Use the command line to send tasks to OmniRoute's A2A server, which supports communication between agents. Inspect execution history and logs, monitor or cancel tasks, and interactively test the JSON-RPC 2.0 communication protocol.

Check server status and available skills
Invoke a skill with JSON input
Inspect task history and logs

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

cli-backup-sync

FreeSummaryAI rating 70

Back up and restore OmniRoute data from the command line. Covers incremental snapshots, encryption, cloud synchronization, scheduled backups, and archive import and export, with options for retention and previewing an import.

Create a backup before changing settings
Schedule recurring backups and set retention
Synchronize data with cloud storage

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

cli-batches

FreeSummary

Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.

Submitting AI requests from a JSONL file
Monitoring batch jobs and waiting for completion
Saving batch results and error details

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

cli-chat

FreeSummaryAI rating 90

Send prompts to LLMs from a terminal, display answers as they arrive, or hold an ongoing conversation. Use files or standard input for prompts, choose models, and set system instructions through OmniRoute.

Sending a prompt from a terminal
Using file contents as a prompt
Displaying and saving streaming responses

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

cli-compression

FreeSummaryAI rating 80

Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.

Preview compression results with real prompts
Adjust RTK filters and Caveman rules
Compare combined compression modes

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

cli-contexts

FreeSummaryAI rating 80

Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.

Adjust context token budgets and filtering rules
Switch between saved server connections
Import or export connection settings as JSON

cheaper-inference/OmniRoute79.8KUpdated Oct 22, 2026

See all skills by cheaper-inference

Report a problem with this skill

Install

Install with a command

npx skills add https://github.com/cheaper-inference/OmniRoute --skill omni-inference

Paste it into your terminal and run it (requires Node.js). You can choose which agents to install it for, such as Claude Code or Codex.

Ask your agent

Please install the following Agent Skill.
https://github.com/cheaper-inference/OmniRoute/tree/release/v3.8.53/skills/omni-inference

First review SKILL.md and the bundled files and confirm there is nothing suspicious (such as sending data externally or reading credentials). Then place it in ~/.claude/skills/omni-inference/ for Claude Code, or ~/.agents/skills/omni-inference/ for Codex.

Send this text to Claude Code or Codex as is. It checks the contents before installing.

View source on GitHub

Repository: cheaper-inference/OmniRoute
Stars: 79,809
Forks: 11,621
Category: Data & AI
License: MIT
Original language: English
Last updated: Oct 22, 2026

A skill is a set of instructions and scripts for an agent. cccskills does not guarantee that skills are safe. Review the contents before you install.