NewPoint any agent at UberLLM — one key, every model, list price or less.
Uber for AI capacity

The world’s best video, image, music & LLM models — dirt cheap

We connect you to unused AI compute and route every request to the cheapest seller. One OpenAI- & Anthropic-compatible key — start in a minute.

https://api.uberllm.dev/v1

Trusted By: 477 models live · 25.5k requests / 30 days

99.9%
Off, live
$0
Monthly fee
$0
On failed requests
Live market statusView models →

One key for every major model

Veo 3 Fast Text-to-VideoKling 2.6 Pro Text-to-VideoNano Banana 2Seedance 2.0 Text-to-VideoGemini Omni FlashFlux 1.1 ProSeedream V5 LiteWan 2.7 Pro

Transparent pricing, built for scale

Leading AI models at a fraction of the cost. One balance, no hidden fees, and you never pay for a failed generation.

Top saving, live

up to 99.9%

off the official price, routed automatically

Failed tasks

$0

zero-risk billing — a failure costs nothing

Hidden fees

None

one balance; 5% card fee only when you add credit

Grok Imagine High Quality
IMAGE

UberLLM

$0.0283

per image

−52%

Official

$0.06

per image

Nano Banana Pro
IMAGE

UberLLM

$0.0882

per image

−51%

Official

$0.18

per image

Flux 2 Max
IMAGE

UberLLM

$0.045

per image

−50%

Official

$0.09

per image

Flux 2 Max — Edit
IMAGE

UberLLM

$0.096

per image

−49%

Official

$0.19

per image

Chroma
IMAGE

UberLLM

$0.0054

per image

−46%

Official

$0.01

per image

FLUX.2 Flex
IMAGE

UberLLM

$0.033

per megapixel

−44%

Official

$0.06

per megapixel

FLUX.2 Klein 4B
IMAGE

UberLLM

$0.0083

per megapixel

−44%

Official

$0.015

per megapixel

Z-Image Turbo
IMAGE

UberLLM

$0.0064

per image

−36%

Official

$0.01

per image

AV-Gen Text-to-Video
VIDEO

UberLLM

$0.14

per second

−29%

Official

$0.2

per second

Wan 2.6 Flash Image-to-Video
VIDEO

UberLLM

$0.042

per second

−25%

Official

$0.056

per second

Wan 2.7 Text-to-Video
VIDEO

UberLLM

$0.44

per second

−20%

Official

$0.55

per second

Kling O3 Pro Text-to-Video
VIDEO

UberLLM

$0.37

per second

−20%

Official

$0.46

per second

Runway Gen-4 Turbo
VIDEO

UberLLM

$0.11

per second

−20%

Official

$0.14

per second

Wan 2.5 Preview Text-to-Video
VIDEO

UberLLM

$0.44

per second

−20%

Official

$0.55

per second

Kling V3 Pro Text-to-Video
VIDEO

UberLLM

$0.44

per second

−20%

Official

$0.55

per second

Grok Imagine Text-to-Video
VIDEO

UberLLM

$0.072

per second

−20%

Official

$0.09

per second

Gemma 4 E2B Input
LLM

UberLLM

$0.002

per 1M tokens

−94%

Official

$0.04

per 1M tokens

Gemma 4 E2B Output
LLM

UberLLM

$0.004

per 1M tokens

−94%

Official

$0.08

per 1M tokens

Mistral Large Input
LLM

UberLLM

$0.1

per 1M tokens

−94%

Official

$2

per 1M tokens

Mistral Large Output
LLM

UberLLM

$0.31

per 1M tokens

−94%

Official

$6

per 1M tokens

GPT-5.4 Input
LLM

UberLLM

$0.15

per 1M tokens

−94%

Official

$2.5

per 1M tokens

GPT-5.4 Output
LLM

UberLLM

$0.87

per 1M tokens

−94%

Official

$15

per 1M tokens

Mistral Large 3 Input
LLM

UberLLM

$0.0291

per 1M tokens

−94%

Official

$0.5

per 1M tokens

Mistral Large 3 Output
LLM

UberLLM

$0.0874

per 1M tokens

−94%

Official

$1.5

per 1M tokens

Chatterbox HD TTS
AUDIO

UberLLM

$0.025

per 1K characters

−50%

Official

$0.05

per 1K characters

Stable Audio 2.5
AUDIO

UberLLM

$0.15

per track

−36%

Official

$0.24

per track

Inworld 1.5 Max TTS
AUDIO

UberLLM

$0.0099

per 1K characters

−21%

Official

$0.0125

per 1K characters

Qwen3 0.6B TTS
AUDIO

UberLLM

$0.0699

per 1K characters

−20%

Official

$0.0875

per 1K characters

Venice TTS 1
AUDIO

UberLLM

$0.0028

per 1K characters

−20%

Official

$0.0035

per 1K characters

Qwen3 1.7B TTS
AUDIO

UberLLM

$0.09

per 1K characters

−20%

Official

$0.11

per 1K characters

Venice Music Gen
AUDIO

UberLLM

$0.024

per track

−19%

Official

$0.03

per track

ElevenLabs Turbo v2.5 TTS
AUDIO

UberLLM

$0.05

per 1K characters

−19%

Official

$0.0625

per 1K characters

Featured models

Top models, live on the market

VID$0.66 per second

Veo 3 Fast Text-to-Video

Google Veo — cinematic text- and image-to-video with sound.

VID$0.77 per second

Kling 2.6 Pro Text-to-Video

Kling — high-motion, photoreal video generation.

IMG$0.08 per image

Nano Banana 2

Google Nano Banana — fast, sharp image generation and editing.

VID$0.31 per second

Seedance 2.0 Text-to-Video

ByteDance Seedance — fast, expressive video generation.

VID$0.14 per second

Gemini Omni Flash

Google Gemini — multimodal models across text, image and more.

IMG$0.024 per image

Flux 1.1 Pro

Black Forest FLUX — state-of-the-art image generation.

IMG$0.041 per image

Seedream V5 Lite

ByteDance Seedream — design-aware, text-faithful image model.

IMG$0.075 per image

Wan 2.7 Pro

Alibaba Wan — long-form, omni-reference video generation.

Developer-first integration

Up and running in minutes on one unified, OpenAI- and Anthropic-compatible API.

Step 01

Keep your SDK

Point the base URL at UberLLM and use the OpenAI or Anthropic SDK you already have. Nothing else in your code changes.

base_url =

https://api.uberllm.dev/v1

api_key = ull_•••••

Step 02

One id, every backend

Switch models by changing the model id — Claude, GPT, Gemini, DeepSeek, or an image, video or music model. Every request routes to the cheapest healthy seller.

LLMIMGVIDAUDVIDLLMAUDIMG
Step 03

Stream, poll or webhook

Text streams back token by token. Image and video jobs return a task you poll, or point a webhook at your app to be notified the moment the result is ready.

Webhook200 OK
PollREADY

Why developers choose UberLLM

We handle the complexity of many providers and sellers, so you can focus entirely on building.

01

Lower-cost access

Pay less than list price

Sellers list spare capacity below the official price, and every request is billed at the cheapest healthy route. Many models land well under official pricing; the deepest savings show live in the table above.

02

Unified API

One key for every model

Reach Claude, GPT, Gemini, DeepSeek and more — plus image, video and music models — through one OpenAI- and Anthropic-compatible endpoint. Change the model id, not your backend.

03

Reliability

Routing that reroutes

When a seller is slow or down, the request moves to the next healthy one automatically. Async task tracking and webhook callbacks keep high-volume media workflows moving.

04

Zero-risk billing

Never pay for a failure

A request or a generation that fails costs nothing. One balance covers everything, with no monthly fee and no hidden charges.

05

Drop-in

Integrate once

Consistent request and task patterns across text, image, audio and video, with clear docs — so your team can adopt a new model without rebuilding anything.

06

Playground

Try before you build

Compare model outputs and tune parameters in the dashboard before you write a line of production code — the same API, in a console.

07

Sell your capacity

Earn on what you don’t use

Have spare AI capacity? List it on the market and earn when requests route to you — the same marketplace, from the other side.

Coding agents

Point your coding agent at UberLLM

One command sets Claude Code to route through UberLLM — the same key, every model, billed at the cheapest healthy seller. Nothing else in your setup changes.

Keep the exact models Claude Code ships with. Opus stays Opus, Sonnet stays Sonnet — routed through the market instead of billed at list.

curl -fsSL https://uberllm.dev/install/claude-code.sh | sh
Download installerSigned in? The download comes with a fresh key already in it.
  1. 1. Run the command
  2. 2. Approve in the browser
  3. 3. Run claude

What technical teams value

Built for the teams shipping the next generation of AI-native products.

477

Models live

25.5k

Requests / 30 days

$0

Charged on failures

One key, every model
Claude, GPT, Gemini, Veo, Kling, Seedance and Suno behind a single key — no more juggling a dozen vendor bills and SDKs.
Zero-risk billing
A failed request or generation costs $0. One balance covers text, image, video and music, with no monthly fee.
Routed to the cheapest seller
Every request lands on the cheapest healthy seller for that model, and reroutes automatically when one slows down.

The live market

Every model that is live right now, the sellers serving it, and the price a request is billed at this moment.

Live · updated 15m ago
108 of 477 models
Category
google/veo3-1-full-image-to-video
Google
VIDEO

UberLLM

be the first seller →
bytedance/seedance-2-0-mini-enhanced-reference-to-video
ByteDance
VIDEO

UberLLM

be the first seller →
lightricks/ltx-2-19b-full-image-to-video
Lightricks
VIDEO

UberLLM

be the first seller →
lightricks/ltx-2-v2-3-full-image-to-video
Lightricks
VIDEO

UberLLM

be the first seller →
pixverse/pixverse-c1-image-to-video
PixVerse
VIDEO

UberLLM

be the first seller →
wan/wan-2-5-preview-image-to-video
Alibaba
VIDEO

UberLLM

be the first seller →
happyhorse/happyhorse-1-0-reference-to-video
HappyHorse
VIDEO

UberLLM

be the first seller →
pixverse/pixverse-v5-6-image-to-video
PixVerse
VIDEO

UberLLM

be the first seller →
bytedance/seedance-2-0-mini-image-to-video
ByteDance
VIDEO

UberLLM

be the first seller →
bytedance/seedance-2-0-enhanced-reference-to-video
ByteDance
VIDEO

UberLLM

be the first seller →
google/veo3-1-fast-image-to-video
Google
VIDEO

UberLLM

be the first seller →
wan/wan-2-7-reference-to-video
Alibaba
VIDEO

UberLLM

be the first seller →
happyhorse/happyhorse-1-1-reference-to-video
HappyHorse
VIDEO

UberLLM

be the first seller →
bytedance/seedance-2-0-mini-reference-to-video
ByteDance
VIDEO

UberLLM

be the first seller →
lightricks/ltx-2-full-image-to-video
Lightricks
VIDEO

UberLLM

be the first seller →
pixverse/pixverse-c1-reference-to-video
PixVerse
VIDEO

UberLLM

be the first seller →
x-ai/grok-imagine-1-5-image-to-video-private
xAI
VIDEO

UberLLM

be the first seller →
vidu/vidu-q3-image-to-video
Vidu
VIDEO

UberLLM

be the first seller →
pixverse/pixverse-c1-transition
PixVerse
VIDEO

UberLLM

be the first seller →

Frequently asked questions

Everything you need to know about integrating and billing with UberLLM.

Still have questions?

The docs cover every endpoint, error and billing detail.

What is UberLLM?

UberLLM is a marketplace for spare AI capacity. People with unused AI capacity sell it below list price, and you buy it through one OpenAI- and Anthropic-compatible key — Claude, GPT, Gemini, DeepSeek and more, for text, image, video and music.

How is it cheaper than going direct?

Sellers list their spare capacity below the official price. Every request you send is routed to the cheapest healthy seller for that model, so you get the lowest available price automatically — the live saving per model is shown in the pricing table.

Which models can I use?

Leading LLMs (Claude, GPT, Gemini, DeepSeek and others) alongside image, video and music models. The market table lists every model that is live right now with its current price.

Do I pay for failed requests?

No. A request or a generation that fails costs $0. You are only billed for results you actually receive.

Is there a monthly fee or minimum?

No monthly fee and no minimum. You keep one balance and pay as you go. A 5% card fee applies only when you add credit — never per request.

Is it OpenAI-compatible?

Yes. Set the base URL to our endpoint and keep your existing OpenAI SDK; the Anthropic-compatible endpoint works the same way. You switch models by changing the model id.

What happens if a seller goes offline?

Your request is routed to the next healthy seller for that model automatically. For image and video jobs, task tracking and webhook callbacks mean an interruption on one seller doesn’t lose your job.

How do you handle my prompts and data?

Keys are scoped and revocable, and requests are encrypted in transit. Your traffic is used to serve your requests — not to train models.

How do I get started?

Create an account, generate a key, point your SDK’s base URL at UberLLM, and send your first request. Add credit when you’re ready to go beyond the free key.

Can I sell my own capacity?

Yes. If you have spare AI capacity you can list it on the market and earn when requests route to you. It is the same marketplace, from the seller’s side.

Start building with the world’s top AI models today

One key for every model, priced below list — and you never pay for a request that fails.

Veo 3 Fast Text-to-VideoKling 2.6 Pro Text-to-VideoNano Banana 2Seedance 2.0 Text-to-VideoGemini Omni FlashFlux 1.1 ProSeedream V5 LiteWan 2.7 Pro