thelastapi
Console
Products

AI

An OpenAI-compatible gateway to every major lab's models, for chat, embeddings, images, video, speech and transcription, metered per call.

Open as .md

One metered entry point for language models, embeddings, images, video, text to speech and speech to text. It is OpenAI-compatible under /v1/ai, so the OpenAI SDK, the AI SDK (@ai-sdk/openai) and most agents work by changing the base URL. Pick a thelastapi model by what it is for (vibiz/fast, vibiz/smart, vibiz/image…), or any lab's model by its own id (anthropic/claude-opus-5.5, moonshotai/kimi-k3.1-pro…). Either way exactly that model runs: thelastapi never swaps in another one.

TypeScript
import OpenAI from 'openai';
const openai = new OpenAI({ baseURL: process.env.VIBIZ_AI_BASE_URL, apiKey: process.env.VIBIZ_AI_API_KEY });
const stream = await openai.chat.completions.create({ model: 'vibiz/fast', messages, stream: true });

Keys

  • Account key (vz_sk_…): agents and scripts. Add X-Vibiz-Project: prj_… to bill a project.
  • Project AI key (vz_ai_…): vibiz add ai. The app's env gets VIBIZ_AI_BASE_URL, VIBIZ_AI_API_KEY and the aliases OPENAI_BASE_URL, OPENAI_API_KEY, so new OpenAI() works unchanged.
  • App key: new OpenAI(vibiz.ai) with @vibiz/app.

Models and pricing

A thelastapi model is a stable name for what it is for. Each runs one lab model, named below and in every answer (served_model); we move a tier to a newer model as labs ship them, and the change shows here. If that model is down, the call fails (model_unavailable or provider_unavailable) rather than run a different model you didn't pay for.

thelastapi modelRuns onForPrice (USD)
vibiz/fast (default chat)GPT-6 Luna (OpenAI)chat, tool calls, JSON$0.10 / $0.50 per million tokens in / out
vibiz/liteDeepSeek V4.1 Flash (DeepSeek)the cheapest chat, 1M token context$0.14 / $0.42
vibiz/smart-miniClaude Haiku 5.5 (Anthropic)quick, strong writing and coding$0.10 / $0.50
vibiz/balancedGemini 3.8 Flash (Google)quality and price balanced, 1M token context$0.825 / $4.125
vibiz/reasoningGPT-6.1 Terra (OpenAI)thinks before it answers: math, logic, planning$1 / $5
vibiz/smartClaude Sonnet 5.5 (Anthropic)hard tasks: writing, coding, agents$2 / $10
vibiz/proClaude Opus 5.5 (Anthropic)the strongest chat tier, long agent runs$4 / $20
vibiz/embedtext-embedding-3-small (OpenAI)embeddings, 1536 dimensions$0.02 per million tokens
vibiz/embed-largetext-embedding-3-large (OpenAI)embeddings, 3072 dimensions$0.13 per million tokens
vibiz/imageNano Banana 2 (Google)fast images, edits, consistent charactersabout $0.067 per image
vibiz/image-proNano Banana 2.1 (Google)Google's newest image modelabout $0.034 per image
vibiz/image-textGPT-5.4 Image 2 (OpenAI)long prompts, text rendered in the imageabout $0.04 per image
vibiz/videoLTX-2.5 Fast (Lightricks)6 s clips at 720p with sound, from a prompt or from an image (image_url), jobs only$0.54 per video
vibiz/voiceEleven v4 Turbo (ElevenLabs)natural real-time voices$0.04 per 1,000 characters
vibiz/voice-proEleven v4 (ElevenLabs)the most expressive voices$0.08 per 1,000 characters
vibiz/voice-liteEleven Flash v2.5 (ElevenLabs)the fastest voices, 32 languages$0.04 per 1,000 characters
vibiz/transcribeScribe v2 (ElevenLabs)speech to text, 99 languages$0.22 per hour of audio

These are the labs' list prices. A call is billed at what it really cost plus the AI fee in the price book (markup_pct on each model in GET /v1/ai/models). Some chat models charge more once a call's input passes a long-context threshold (pricing.long_context): GPT-6 models past 272,000 input tokens, Claude Haiku 5.5 past 100,000. Every JSON response carries cost_micro_usd, the exact cost of that call, and served_model (speech: the X-Vibiz-Served-Model header).

All models

Beyond the thelastapi models, every language model from every major lab runs by its own id: OpenAI, Anthropic, Google, DeepSeek, xAI, Moonshot AI, Qwen, Mistral, Meta, MiniMax, Z.ai and more, over 400 in all, kept current as labs release them. Search them in the console (AI models), with GET /v1/ai/models?all=1&q=kimi, vibiz ai models kimi, or the vibiz_ai_models tool.

JSON
{ "model": "moonshotai/kimi-k3.1-pro", "messages": [{ "role": "user", "content": "Hi" }] }

It runs exactly that model, at its list price plus the AI fee, and the answer names it. Usage groups a model behind a thelastapi model under that thelastapi model, and any other model under its own id. The media models above (google/gemini-nano-banana-2.1, elevenlabs/v4…) and older ones (black-forest-labs/flux-schnell, openai/whisper-1…) are called by id the same way. A model that isn't in the list can't be called (invalid_request, param: "model"), so a typo can't reach an expensive model.

Video takes 16:9 or 9:16 (1:1 comes back as 16:9).

Limits

Daily spend ceiling$5 per account per UTC day by default (AI and actions together; an owner raises it in Billing); each call is held at its worst case before it runs
Creditseach call's worst case must fit in the account's balance (plus $0.50); out of credits: 402 payment_required (Billing)
Project budget$1 per project per UTC day by default; the owner changes it in the console ▸ project ▸ AI ▸ Daily AI budget or PATCH /v1/projects/:id/ai { daily_budget_usd, end_user_daily_budget_usd } (null: none). Past it: 429, details.reason: "project_budget", raise_url
Alertsthe owners get an email at 80 % and 100 % of the daily spend limit and of each project's budget, and a banner on Overview and Usage, with a link that raises it (Usage ▸ Limit alerts)
max_tokens1,024 when not given, at most 16,384 (per model)
Images4 per request, 256–2,048 px a side
Speech4,096 characters
Transcription25 MB upload
Embeddings2,048 inputs
Rate, account key300 requests and 400k tokens a minute, 50 in flight
Rate, project key120 requests and 200k tokens a minute (settable to 600 and 2M), 25 in flight (up to 50)
Over the in-flight limitthe call waits for a free slot, first come first served, up to 60 s (it stops waiting if the caller disconnects), so a batch of images all goes through as slots free up; only after that wait is it 429, details.reason: "concurrency"
Media linkspermanent with a project (Files); 24 hours without one

Building an app on AI: tell the owner the project budget and the account's daily spend limit it runs under and what you expect it to cost a day, and set daily_budget_usd to fit the expected traffic. A cap the app adds itself stays under these and tells the owner when it is hit: an app must never stop silently.

Use it

Terminal
curl https://thelastapi.dev/v1/ai/chat/completions \
  -H "Authorization: Bearer $VIBIZ_API_KEY" -H 'content-type: application/json' \
  -d '{"model":"vibiz/fast","messages":[{"role":"user","content":"Name a bakery in three words."}]}'
Terminal
vibiz ai "Name a bakery in three words."
vibiz image "a croissant on a marble table" -o hero.png
vibiz say "Welcome to Acme Bakery" -o welcome.mp3 --voice alloy
vibiz transcribe call.m4a --language en

Agents use vibiz_ai_chat, vibiz_image_generate, vibiz_speech_create and vibiz_speech_transcribe; media comes back as links, never base64; with a project the link is permanent and the file is in the project's Files (vibiz_files). The same as actions: POST /v1/actions/ai.chat { "input": { "prompt": "…" } }.

RouteDoes
POST /v1/ai/chat/completionschat, streaming (SSE) or not; tools, JSON mode
POST /v1/ai/embeddingsembeddings
POST /v1/ai/images/generationsimages: b64_json (default) or url
POST /v1/ai/audio/speechtext to speech, streamed mp3 or pcm
POST /v1/ai/audio/transcriptionsspeech to text, multipart file
POST /v1/ai/jobs, GET /v1/ai/jobs/:idslow images and video: 202, then poll. Video: { "type": "video", "model": "vibiz/video", "input": { "prompt": "…", "image_url": "https://…" (optional: animate this still), "aspect_ratio": "16:9" | "9:16" } }. From an agent: vibiz_video_generate; from a terminal: vibiz video "<prompt>" -o out.mp4 [--from-image <url>]
GET /v1/ai/models, GET /v1/ai/healthcatalogue with prices; per capability ok/degraded/down

Voices are alloy, ash, coral, echo, fable, nova, onyx, sage, shimmer. Pass your own user's id as user (or X-Vibiz-User) and spend breaks down per end user.

Generated media is kept in Files

Every image, video and audio you generate is saved in the project's Files, with the model, the prompt and the cost. Use the url in the response (it is permanent), or vibiz files latest / vibiz files search "<prompt words>" later.

Files are named by date and prompt (2026-10-28-cold-email-cover.png). A call with a development key (the development app key or AI key) saves to the development Files; every other project call saves to production. A call billed to the account with no project has no Files to go to: it is not saved and its links expire after 24 hours. Saving never fails the call: if it can't be saved, you get the 24-hour link and no file fields.

The answers keep their OpenAI shape and add:

CallAdded
POST /v1/ai/images/generationsfile_id and file_url on each data[i]; with response_format: "url", url is the permanent link
POST /v1/ai/jobs (image and video), once donefile_id and file_url on each output.data[i]; url is permanent and expires_at is null
POST /v1/ai/audio/speechheaders X-Vibiz-File-Id and X-Vibiz-File-Url (the file appears once the audio has finished)
actions image.generate, speech.createurl permanent, plus file_id and file_url

Your own keys

Have Google Cloud credits, or a Google account you'd rather pay? Add your own Google key and Google's models run on your Google account: Google bills you, and the call costs 0 on thelastapi (each answer says "paid_by": "your_key", with would_cost_micro_usd: what it would have cost here). Models from other labs keep running on thelastapi, billed as usual: your key never moves a thelastapi model to a Gemini model.

Two kinds of Google credentials:

TypeWhat it isServes
"gemini_api_key"a Gemini API key from Google AI StudioGoogle's chat, image, video, speech and transcription models, and embeddings if you turn them on
"vertex"a Google Cloud service account key file, a project id and a region (default global): Vertex AI, which spends Google Cloud creditsGemini 3.1 Flash Lite, 3.5 Flash Lite and 3.5 Flash chat, and transcription, today; the rest stays on thelastapi
Terminal
GEMINI_API_KEY=… vibiz ai keys set google          # or type it at the hidden prompt
vibiz ai keys set google --vertex sa.json --region us-central1
vibiz ai keys                                       # status, and which models run on your key
vibiz ai keys test google
vibiz ai keys remove google

Or in the console: API keys ▸ Your AI keys. With the API: PUT /v1/ai-keys/google { "type": "gemini_api_key", "api_key": "…" } (full-access keys only). A key is checked with a free call to Google before it is saved, and refused with the reason if Google refuses it. It is stored encrypted and never shown again: only its last 4 characters, when it was last used and its last error. A project can have its own key (/v1/projects/:id/ai-keys/google), which replaces the account's for that project.

What to know:

  • No silent fallback. A call your key can serve runs only on your key. If Google refuses it or is down, the call fails (provider_failed, details.reason: "customer_key_rejected", or provider_unavailable): it is never retried on thelastapi's account, so you are never billed by us by surprise.
  • What runs on your key: any google/… model by its id (google/gemini-4-argon, google/gemini-3.8-flash-tts, google/gemini-omni-1.1-flash, google/gemini-embedding-2…), and the thelastapi models whose model is Google's: vibiz/balanced (Gemini 3.8 Flash), vibiz/image (Nano Banana 2) and vibiz/image-pro (Nano Banana 2.1).
  • Everything else runs on thelastapi, billed as usual: the key's status lists every thelastapi model with paid_by: "your_key" or "vibiz".
  • Embeddings are off by default (use_for): vectors from another model don't match the ones your index already holds, and nothing would error. Turn them on for a new index: PATCH /v1/ai-keys/google { "use_for": ["llm", "embeddings", …] }.
  • Speech on your Google key comes back as WAV (audio/wav) when you ask for mp3: we don't convert audio. pcm is the same 24 kHz 16-bit mono PCM as always.
  • Transcription on your Google key takes files up to 14 MB, and video takes 16:9 or 9:16.
  • A job made on your key fails if you remove the key before it runs; it never runs on ours.

Your own fal key

Add your own fal key and images and video run on your fal account: your fal balance pays, and the call costs 0 on thelastapi. Your key also runs any fal endpoint by its id.

Terminal
vibiz ai keys add fal                       # hidden prompt; or FAL_KEY=… / --key-file key.txt
vibiz ai keys test fal
vibiz ai keys remove fal

Get the key at fal.ai/dashboard/keys (it looks like key-id:secret), or add it in the console: API keys ▸ Your AI keys ▸ Add your fal key. With the API: PUT /v1/ai-keys/fal { "type": "fal_key", "api_key": "…" }. It is checked with a free call to your fal account first (nothing is generated) and refused with the reason if the key is wrong. A project can have its own (/v1/projects/:id/ai-keys/fal).

  • What runs on it: vibiz/video, the Flux image models by id (black-forest-labs/flux-schnell, black-forest-labs/flux-dev), and any image or video model by its id (below). The key's status lists every thelastapi model with paid_by.
  • Edit a photo (start from one or more photos): add image_url (one public https link, a Files link works) or image_urls (up to 8, to combine a person and a product, a face and an outfit) to POST /v1/ai/images/generations; the prompt says what to change. Works with vibiz/image, vibiz/image-pro (Nano Banana) and vibiz/image-text; a model that only draws from a prompt answers 400 with details.reason: "model_takes_no_photo" rather than ignoring the photo. Image jobs take the same fields inside input. MCP: vibiz_image_generate { prompt, image_url }; CLI: vibiz image "make the background a beach" -o out.png --from-image <url>.
    TypeScript
    await openai.images.generate({ model: 'vibiz/image', prompt: 'make the background a beach', image_url: 'https://…/me.jpg' } as never);
  • Any image or video model by its id, on credit: not only the thelastapi models. Find one with GET /v1/ai/media-models?q=kling (SDK vibiz.ai.mediaModels({ q }), MCP vibiz_media_models, CLI vibiz media-models kling): Kling, Seedance, Veo, Hailuo, Wan, face swap, lip sync, upscalers, background removal, try-on… each with its live price (unit: image, megapixel, video or seconds). Run it with model: "<id>" on POST /v1/ai/images/generations (images) or POST /v1/ai/jobs (video and long renders), with the model's own parameters in model_input (images: top level; jobs: inside input), up to 16 KB. It is charged from credits at its live price (per second: the duration asked, 5 s when unsaid); one call is capped at $10 (call_too_expensive). An id no model has answers 400 unknown_model. With the account's own key for that route, it runs on that key instead (cost 0):
    TypeScript
    await vibiz.ai.jobs.create({ type: 'video', model: 'kling-video/v2.1/master/image-to-video', input: { prompt: 'she smiles', image_url: 'https://…/face.png', model_input: { duration: '10' } } });
    await openai.images.generate({ model: 'easel-ai/advanced-face-swap', prompt: 'swap', model_input: { face_image_0: 'https://…/a.png', target_image: 'https://…/b.png' } } as never);
    The prompt and the safety checker stay ours, and only images and video come back. (fal_input still works as the older name of model_input.)
  • No fallback, costs 0: a call your fal key serves never runs on thelastapi's account. If it fails, the call fails:
What happenedErrorFix
Your fal key was refused (wrong, revoked)provider_failed, details.reason: "customer_key_rejected": "Your fal key was refused: replace it in API keys ▸ Your AI keys."Copy a new key from fal.ai/dashboard/keys and replace it
your fal account is out of balanceprovider_failed, details.reason: "customer_key_out_of_credit": "Your fal account is out of credit: top up at fal.ai/dashboard/billing, then try again."Top up at fal.ai/dashboard/billing
Your fal account is rate limited429 rate_limited with retry_after_secondsWait that long

The key's status shows the last error (last_error) until a call succeeds or Test passes.

What agents can and can't do

Agents may call every AI route and tool; each call is metered and held against the daily ceiling. Rotating the project's production AI key is an owner's (POST /v1/projects/:id/ai/keys/rotate), and so are setting and removing your own provider keys; agents can read their status (vibiz_ai_keys), never a secret.

Errors

OpenAI-shaped, so OpenAI SDKs read them: { "error": { "code", "message", "type", "param", "details"? } }.

CodeStatusWhenNext step
invalid_request400bad input, unknown model, a cap exceeded; param names the fieldfix the field
content_filtered400a content filter refused the requestchange the prompt
context_length_exceeded400the input is longer than the model's windowshorten it
payload_too_large413body or upload over its capsend less
unauthorized401missing, invalid or revoked keycheck the key
rate_limited429details.reason: daily_spend, project_budget, end_user_budget, requests_per_minute, tokens_per_minute, concurrencywait (Retry-After), or raise the budget; daily_spend resets at midnight UTC
provider_unavailable503every route failed; details.reason timeout, stall, circuit_openretry later
model_unavailable503no route can run that model right now; thelastapi never swaps in anotherretry after details.retry_after_seconds, or pick another model
not_configured503this model can't be served right nowuse another thelastapi model

Mid-stream, the error arrives as a final SSE event, data: {"error": {…}}, without [DONE].