9Router — Chat

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Endpoints

• POST $NINEROUTER_URL/v1/chat/completions — OpenAI format
• POST $NINEROUTER_URL/v1/messages — Anthropic format

Discover

curl $NINEROUTER_URL/v1/models | jq '.data[].id'
# Per-model metadata (contextWindow, params)
curl "$NINEROUTER_URL/v1/models/info?id=openai/gpt-4o"

Combos (e.g. vip, mycodex) auto-fallback through multiple providers.

OpenAI format

curl -X POST $NINEROUTER_URL/v1/chat/completions \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5","messages":[{"role":"user","content":"Hi"}],"stream":false}'

JS (OpenAI SDK):

import OpenAI from "openai";
const client = new OpenAI({ baseURL: `${process.env.NINEROUTER_URL}/v1`, apiKey: process.env.NINEROUTER_KEY });
const res = await client.chat.completions.create({
  model: "openai/gpt-5",
  messages: [{ role: "user", content: "Hi" }],
  stream: true,
});
for await (const chunk of res) process.stdout.write(chunk.choices[0]?.delta?.content || "");

Anthropic format

curl -X POST $NINEROUTER_URL/v1/messages \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model":"cc/claude-opus-4-7","max_tokens":1024,"messages":[{"role":"user","content":"Hi"}]}'

Response shape

OpenAI (/v1/chat/completions):

{ "id": "chatcmpl-...", "object": "chat.completion", "model": "openai/gpt-5",
  "choices": [{ "index": 0, "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 8, "completion_tokens": 2, "total_tokens": 10 } }

Streaming (stream:true) emits SSE: data: {choices:[{delta:{content:"..."}}]}\n\n ... data: [DONE]\n\n.

Anthropic (/v1/messages):

{ "id": "msg_...", "type": "message", "role": "assistant", "model": "cc/claude-opus-4-7",
  "content": [{ "type": "text", "text": "Hello!" }],
  "stop_reason": "end_turn", "usage": { "input_tokens": 8, "output_tokens": 2 } }

9Router — Embeddings

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

curl $NINEROUTER_URL/v1/models/embedding | jq '.data[].id'
# Per-model dimensions
curl "$NINEROUTER_URL/v1/models/info?id=openai/text-embedding-3-small"

Endpoint

POST $NINEROUTER_URL/v1/embeddings

Examples

curl -X POST $NINEROUTER_URL/v1/embeddings \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/text-embedding-3-small","input":["hello","world"]}'

JS:

const r = await fetch(`${process.env.NINEROUTER_URL}/v1/embeddings`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "gemini/text-embedding-004", input: "RAG chunk text" }),
});
const { data } = await r.json();
console.log(data[0].embedding.length);  // dimension

Response shape

{ "object": "list", "model": "openai/text-embedding-3-small",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0123, -0.045, ...] },
    { "object": "embedding", "index": 1, "embedding": [...] }
  ],
  "usage": { "prompt_tokens": 5, "total_tokens": 5 } }

Provider quirks

Batch (input as array) is faster; some providers cap batch size.

9Router — Image Generation

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

curl $NINEROUTER_URL/v1/models/image | jq '.data[].id'
# Per-model params/options (size enum, quality enum, capabilities like edit)
curl "$NINEROUTER_URL/v1/models/info?id=openai/dall-e-3"

Endpoint

POST $NINEROUTER_URL/v1/images/generations

Add query ?response_format=binary to receive raw image bytes (handy for saving file).

Examples

Save to file (binary):

curl -X POST "$NINEROUTER_URL/v1/images/generations?response_format=binary" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini/gemini-3-pro-image-preview","prompt":"watercolor mountains at sunrise","size":"1024x1024"}' \
  --output out.png

JS (URL response):

const r = await fetch(`${process.env.NINEROUTER_URL}/v1/images/generations`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "gemini/gemini-3-pro-image-preview", prompt: "neon city", size: "1024x1024" }),
});
const { data } = await r.json();
console.log(data[0].url || data[0].b64_json.slice(0, 40));

Response shape

JSON (default response_format=url):

{ "created": 1735000000, "data": [{ "url": "https://..." }] }

response_format=b64_json:

{ "created": 1735000000, "data": [{ "b64_json": "iVBORw0KGgo..." }] }

Query ?response_format=binary returns raw image bytes (Content-Type image/png or image/jpeg).

Provider quirks

Common fields above work everywhere. These add/override:

9Router — Speech-to-Text

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

curl $NINEROUTER_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$NINEROUTER_URL/v1/models/info?id=openai/whisper-1"

model = STT model ID (e.g. openai/whisper-1, groq/whisper-large-v3, deepgram/nova-3, gemini/gemini-2.5-flash).

Endpoint

POST $NINEROUTER_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)

Examples

curl -X POST "$NINEROUTER_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -F "model=openai/whisper-1" \
  -F "file=@audio.mp3" \
  -F "language=vi"

JS (Node):

import { createReadStream } from "node:fs";
const form = new FormData();
form.append("model", "groq/whisper-large-v3-turbo");
form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");
const r = await fetch(`${process.env.NINEROUTER_URL}/v1/audio/transcriptions`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}` },
  body: form,
});
const { text } = await r.json();
console.log(text);

Response shape

Default (response_format=json):

{ "text": "Xin chào, đây là bản ghi âm." }

verbose_json adds language, duration, segments[] with timestamps. srt / vtt return subtitle text.

Provider quirks

9Router — Text-to-Speech

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

# 1) List models
curl $NINEROUTER_URL/v1/models/tts | jq '.data[].id'
# 2) Per-model metadata (params, voicesUrl if voice-by-id)
curl "$NINEROUTER_URL/v1/models/info?id=el/eleven_multilingual_v2"
# 3) List voices (elevenlabs, edge-tts, deepgram, inworld, local-device). Optional ?lang=vi
curl "$NINEROUTER_URL/v1/audio/voices?provider=edge-tts&lang=vi" | jq '.data[].model'

model field in /v1/audio/speech = voice ID directly (e.g. edge-tts/vi-VN-HoaiMyNeural, el/<voice_id>, or openai/tts-1 model+default voice).

Endpoint

POST $NINEROUTER_URL/v1/audio/speech

Query ?response_format=mp3 (default, raw bytes) or ?response_format=json ({audio: base64, format}).

Examples

Save MP3:

curl -X POST "$NINEROUTER_URL/v1/audio/speech" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/tts-1","input":"Hello world"}' \
  --output speech.mp3

JS (save file):

import { writeFile } from "node:fs/promises";
const r = await fetch(`${process.env.NINEROUTER_URL}/v1/audio/speech`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "el/eleven_multilingual_v2", input: "Xin chào" }),
});
await writeFile("speech.mp3", Buffer.from(await r.arrayBuffer()));

Response shape

Default → raw audio bytes (Content-Type audio/mp3).

?response_format=json:

{ "audio": "SUQzBAAAA...", "format": "mp3" }

Provider quirks (model format)

9Router — Video Generation (xAI Grok Imagine)

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Requires a connected xAI account in the 9Router dashboard — either Grok Build OAuth (SuperGrok / X Premium+ subscription sign-in) or a direct xAI API key from console.x.ai. The two are separate auth types with separate billing; the dashboard shows which one each connection uses.

Endpoints (async job flow)

Video generation is asynchronous: the POST returns a request_id immediately, then you poll until the job is done or failed.

Request fields (passed through to xAI unchanged — see https://docs.x.ai/developers/rest-api-reference/inference/videos):

Examples

Submit a job:

curl -X POST "$NINEROUTER_URL/v1/videos/generations" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"xai/grok-imagine-video","prompt":"A cinematic tracking shot through a neon city at night","duration":8,"aspect_ratio":"16:9","resolution":"720p"}'
# → {"request_id":"abc123"}   (response header x-9router-connection-id: <id>)

Poll until done (echo the connection header back so the same account polls the job):

curl "$NINEROUTER_URL/v1/videos/abc123" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "x-connection-id: <id from create response>"
# → {"status":"pending","progress":42}
# → {"status":"done","video":{"url":"https://…mp4","duration":8},"model":"grok-imagine-video"}
# → {"status":"failed","error":{"code":"…","message":"…"}}

Download: fetch video.url from the done response.

CLI one-shot

9router xai video \
  --prompt "A cinematic tracking shot through a neon city at night" \
  --output video.mp4
# options: --model --duration --aspect-ratio --resolution --image --timeout --port --api-key

Submits, polls with progress, downloads to video.mp4.part, atomically renames on success. Ctrl+C cancels cleanly; non-zero exit on failure.

Notes & limits

• Jobs are account-bound upstream: poll with the same connection that created the job (x-connection-id header, value from the create response's x-9router-connection-id).
• Creation POSTs are never auto-retried (a retry could create and bill two videos). Only a 401→token-refresh→single-retry is performed, which upstream rejects before job creation.
• Video models are tagged kind: "video" and are excluded from chat model lists and chat fallback combos.
• Grok Build subscription OAuth tokens are sent to the same api.x.ai/v1/videos endpoints as API keys; whether a given subscription tier includes video-generation quota is controlled by xAI and is not verified by 9Router — a 403/permission_denied from upstream means the connected account has no video access.

9Router — Web Fetch

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

curl $NINEROUTER_URL/v1/models/web | jq '.data[] | select(.kind=="webFetch") | .id'
# Per-provider params
curl "$NINEROUTER_URL/v1/models/info?id=firecrawl/fetch"

IDs end in /fetch (e.g. firecrawl/fetch, jina/fetch). fetch-combo chains providers with auto-fallback.

Endpoint

POST $NINEROUTER_URL/v1/web/fetch

Examples

Jina Reader

curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"jina-reader","url":"https://9router.com","format":"markdown"}'

Exa

curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"exa","url":"https://example.com","format":"markdown","max_characters":0}'

Firecrawl

curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"firecrawl","url":"https://example.com","format":"markdown","max_characters":0}'

Tavily

curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily","url":"https://example.com","format":"markdown","max_characters":0}'

JS:

const r = await fetch(`${process.env.NINEROUTER_URL}/v1/web/fetch`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "fetch-combo", url: "https://example.com", format: "markdown", max_characters: 5000 }),
});
const { data } = await r.json();
console.log(data.title, data.content.length);

Response shape

{
  "provider": "jina-reader",
  "url": "...",
  "title": "...",
  "content": { "format": "markdown", "text": "...", "length": 1234 },
  "metadata": { "author": null, "published_at": null, "language": null },
  "usage": { "fetch_cost_usd": 0 },
  "metrics": { "response_time_ms": 850, "upstream_latency_ms": 700 }
}

Provider quirks

9Router — Web Search

Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.

Discover

curl $NINEROUTER_URL/v1/models/web | jq '.data[] | select(.kind=="webSearch") | .id'
# Per-provider params (searchTypes, maxResults, required options like cx for google-pse)
curl "$NINEROUTER_URL/v1/models/info?id=tavily/search"

IDs end in /search (e.g. tavily/search). Combos (owned_by:"combo") chain providers with auto-fallback.

Endpoint

POST $NINEROUTER_URL/v1/search

Examples

curl -X POST $NINEROUTER_URL/v1/search \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily","query":"9Router open source","max_results":5}'

JS:

const r = await fetch(`${process.env.NINEROUTER_URL}/v1/search`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "search-combo", query: "latest LLM benchmarks", max_results: 10 }),
});
console.log(await r.json());

Response shape

{
  "provider": "tavily",
  "query": "9Router open source",
  "results": [
    {
      "title": "...", "url": "https://...", "display_url": "github.com/...",
      "snippet": "...", "position": 1, "score": 0.92,
      "published_at": null, "favicon_url": null, "content": null,
      "metadata": { "author": null, "language": null, "source_type": null, "image_url": null },
      "citation": { "provider": "tavily", "retrieved_at": "2026-...", "rank": 1 }
    }
  ],
  "answer": null,
  "usage": { "queries_used": 1, "search_cost_usd": 0.008 },
  "metrics": { "response_time_ms": 850, "upstream_latency_ms": 700, "total_results_available": 12 },
  "errors": []
}

Provider quirks

All accept query + max_results. Optional fields vary:

Provider IS the model — "provider":"tavily" ≡ "model":"tavily".

9Router

Local/remote AI gateway exposing OpenAI-compatible REST. One key, many providers, auto-fallback.

Setup

export NINEROUTER_URL="http://localhost:20128"      # or VPS / tunnel URL
export NINEROUTER_KEY="sk-..."                      # from Dashboard → Keys (only if requireApiKey=true)

All requests: ${NINEROUTER_URL}/v1/... with header Authorization: Bearer ${NINEROUTER_KEY} (omit if auth disabled).

Verify: curl $NINEROUTER_URL/api/health → {"ok":true}

Discover models

curl $NINEROUTER_URL/v1/models                  # chat/LLM (default)
curl $NINEROUTER_URL/v1/models/image            # image-gen
curl $NINEROUTER_URL/v1/models/tts              # text-to-speech
curl $NINEROUTER_URL/v1/models/embedding        # embeddings
curl $NINEROUTER_URL/v1/models/web              # web search + fetch (entries have `kind` field)
curl $NINEROUTER_URL/v1/models/stt              # speech-to-text
curl $NINEROUTER_URL/v1/models/image-to-text    # vision

Use data[].id as model field in requests. Combos appear with owned_by:"combo".

Response shape:

{ "object": "list", "data": [
  { "id": "openai/gpt-5", "object": "model", "owned_by": "openai", "created": 1735000000 },
  { "id": "tavily/search", "object": "model", "kind": "webSearch", "owned_by": "tavily", "created": 1735000000 }
]}

Capability skills

When the user needs a specific capability, fetch that skill's SKILL.md from its raw URL:

Errors

• 401 → set/refresh NINEROUTER_KEY (Dashboard → Keys)
• 400 Invalid model format → check model exists in /v1/models/<kind>
• 503 All accounts unavailable → wait retry-after or add another provider account