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

Video, image, music & LLM models with one key, below list price

Call Claude, GPT, Gemini, DeepSeek, Veo, Kling and hundreds more through one OpenAI- & Anthropic-compatible key. Each request goes to a third-party provider that serves the model, and you pay what it charged. No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Get an API keyStart at $0, pay per useSee pricesEvery model, live

How UberLLM works: where the capacity comes from

https://api.uberllm.dev/v1

Sign in with Google or a one-time code sent by email.

$5 gets you up to $6,250 of AI

valued at the model makers' official prices

ModelOfficialYou payOff
DeepSeek V4.1 Flash$1,315$5−99.62%
DeepSeek V4 Pro$6,250$5−99.92%
Kimi K3$724$5−99.31%
GLM 5.3$520$5−99.04%
GPT-6 Luna$167$5−97%
Claude Haiku 5.5$50$5−90%
Kling 3.010 videos for $5$7$5−30%

Live market prices, updated every hour; a video is a 5-second clip. Top up from $5.

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

One key for every major model

Claude Haiku 5.5Veo 3.1 Lite Text to VideoGPT-6 LunaKling 2.1 StandardNano Banana 2 LiteSeedance 1.0 ProGemini 3.1 Flash LiteFLUX.2 Klein 4B

Where the capacity comes from

UberLLM does not run models. Each request goes to a seller that serves the model through its own account with an API provider (for Claude, GPT and Gemini: the model maker, or a provider such as Amazon Bedrock, Snowflake, Venice AI or OpenRouter), at a price the seller sets below list. Sellers must own or be authorized to resell the access they list under their provider’s terms; stolen, leaked, shared, free-trial and evaluation keys are prohibited. A request that fails is not billed. How it works and why prices can be far below list

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 list price, routed automatically

Failed tasks

$0

zero-risk billing — a failure costs nothing

Fee on requests

None

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Kimi K3
LLM

UberLLM

$0.0032 / $0.25

per 1M tokens, in / out

−98%

List price

$0.19 / $15.00

per 1M tokens, in / out

Qwen3.8 Flash
LLM

UberLLM

$0.0031 / $0.0099

per 1M tokens, in / out

−97%

List price

$0.15 / $0.47

per 1M tokens, in / out

GLM 5.3
LLM

UberLLM

$0.0022 / $0.0448

per 1M tokens, in / out

−96%

List price

$0.0699 / $1.40

per 1M tokens, in / out

DeepSeek V4.1 Flash
LLM

UberLLM

$0.0065 / $0.072

per 1M tokens, in / out

−85%

List price

$0.045 / $0.50

per 1M tokens, in / out

Gemini 3.1 Flash Lite
LLM

UberLLM

$0.0385 / $0.23

per 1M tokens, in / out

−84%

List price

$0.25 / $1.50

per 1M tokens, in / out

Grok 4.7
LLM

UberLLM

$0.84 / $2.51

per 1M tokens, in / out

−58%

List price

$2.00 / $6.00

per 1M tokens, in / out

GPT-6 Luna
LLM

UberLLM

$0.0545 / $0.27

per 1M tokens, in / out

−45%

List price

$0.10 / $0.50

per 1M tokens, in / out

Claude Haiku 5.5
LLM

UberLLM

$0.0672 / $0.34

per 1M tokens, in / out

−32%

List price

$0.10 / $0.50

per 1M tokens, in / out

Wan 2.6 Flash Image-to-Video
VIDEO

UberLLM

$0.02

per second

−64%

List price

$0.056

per second

Kling 2.6 Pro Text-to-Video
VIDEO

UberLLM

$0.055

per second

−64%

List price

$0.15

per second

Kling 2.6 Pro
VIDEO

UberLLM

$0.055

per second

−64%

List price

$0.15

per second

Wan 2.6 Text-to-Video
VIDEO

UberLLM

$0.07

per second

−57%

List price

$0.17

per second

Kling 3 Standard Text to Video
VIDEO

UberLLM

$0.0672

per second

−20%

Fal price

$0.084

per second

Veo 3.1 Fast Text to Video
VIDEO

UberLLM

$0.08

per second

−20%

Fal price

$0.10

per second

Wan 2.7 Text to Video
VIDEO

UberLLM

$0.08

per second

−20%

Fal price

$0.10

per second

Kling 3 Pro Text to Video
VIDEO

UberLLM

$0.0896

per second

−20%

Fal price

$0.11

per second

GPT Image 2 — Edit
IMAGE

UberLLM

$0.03

per image

−91%

List price

$0.36

per image

GPT Image 2
IMAGE

UberLLM

$0.03

per image

−88%

List price

$0.27

per image

Nano Banana 2.1
IMAGE

UberLLM

$0.02

per image

−80%

List price

$0.10

per image

Grok Imagine 2.0
IMAGE

UberLLM

$0.02

per image

−75%

List price

$0.0815

per image

FLUX.2 Klein 4B
IMAGE

UberLLM

$0.0037

per megapixel

−75%

List price

$0.015

per megapixel

Flux 2 Pro
IMAGE

UberLLM

$0.0075

per image

−75%

List price

$0.03

per image

Seedream 4.5
IMAGE

UberLLM

$0.01

per image

−75%

List price

$0.04

per image

Grok Imagine High Quality
IMAGE

UberLLM

$0.015

per image

−75%

List price

$0.06

per image

MiniMax Music 2.5
AUDIO

UberLLM

$0.13

per track

−47%

List price

$0.24

per track

MiniMax Music 2.6
AUDIO

UberLLM

$0.13

per track

−47%

List price

$0.24

per track

Stable Audio 2.5
AUDIO

UberLLM

$0.13

per track

−44%

List price

$0.24

per track

Kokoro Text to Speech
AUDIO

UberLLM

$0.0024

per 1K characters

−30%

List price

$0.0035

per 1K characters

Venice TTS 1
AUDIO

UberLLM

$0.0024

per 1K characters

−30%

List price

$0.0035

per 1K characters

MMAudio V2 Text-to-Audio
AUDIO

UberLLM

$0.007

per track

−30%

List price

$0.01

per track

xAI v1 TTS
AUDIO

UberLLM

$0.0131

per 1K characters

−30%

List price

$0.0187

per 1K characters

ElevenLabs Sound Effects v2
AUDIO

UberLLM

$0.014

per track

−30%

List price

$0.02

per track

Compare all models & sellers →
Featured models

Top models, live on the market

LLMfrom $0.0672 / 1M

Claude Haiku 5.5

Anthropic’s frontier models — top-tier reasoning, tools and long context.

OnlineTry model →
VID$0.024 / job

Veo 3.1 Lite Text to Video

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

OnlineTry model →
LLMfrom $0.0545 / 1M

GPT-6 Luna

OpenAI’s latest GPT models for chat, code and tool use.

OnlineTry model →
VID$0.025 / job

Kling 2.1 Standard

Kling — high-motion, photoreal video generation.

OnlineTry model →
IMG$0.02 per image

Nano Banana 2 Lite

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

OnlineTry model →
VID$0.014 / job

Seedance 1.0 Pro

ByteDance Seedance — fast, expressive video generation.

OnlineTry model →
LLMfrom $0.0385 / 1M

Gemini 3.1 Flash Lite

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

OnlineTry model →
IMGabout $0.0039 per image

FLUX.2 Klein 4B

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

OnlineTry model →

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 set their prices below list price, and cheaper offers that are working get more of the requests. Many models land well under list price; 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

List capacity you may resell

Run your own GPUs or hold provider credits whose plan permits resale? List them on the market and earn when requests route to you.

Coding agents

Point your coding agent at UberLLM

Two environment variables point Claude Code at UberLLM. The same key reaches every model. 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.

Set it up by hand

bash
# Make a key at https://uberllm.dev/dashboard/keys, then:
export ANTHROPIC_BASE_URL=https://api.uberllm.dev
export ANTHROPIC_AUTH_TOKEN=ull_your_key
claude

Lasts for this terminal. To keep it, put the same values in the env block of ~/.claude/settings.json. Guide

Prefer an installer? The Claude Code page has the script, its SHA-256 and how to check it before you run it.

What technical teams value

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

467

Models live

$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.

Models and current prices

Every model you can buy right now, at its current price. A request costs what its provider charged, with no UberLLM fee.

Live · updated 8m ago
Category

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.

Read the docs →Quickstart →
What is UberLLM?

UberLLM is one OpenAI- and Anthropic-compatible API key for Claude, GPT, Gemini, DeepSeek and other text, image, video and music models, usually below list price. Each request is served by a third-party provider and billed what that provider charged.

How is it cheaper than going direct?

Sellers set their own prices as a discount off the model’s list price, and cheaper offers that are working get more of the requests. Sellers must have the right to resell what they list under their provider’s terms. The live price per model is in the pricing table; how it works is at uberllm.dev/how-it-works.

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 fee, a monthly fee or a minimum?

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50. There is no monthly fee and no minimum spend: add credit from $5, keep one balance and pay as you go. Credit does not expire while your account is open.

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 a free account, add credit (from $5), generate a key, point your SDK’s base URL at UberLLM, and send your first request. New accounts start at $0, so add credit before your first call.

Is UberLLM part of Uber?

No. UberLLM is not affiliated with Uber Technologies, Inc.

Can I sell my own capacity?

Yes, if you have the right to resell it under your provider’s terms: your own GPUs, a self-hosted open-weights model, or provider credits under a plan that permits resale. See uberllm.dev/sell.

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.

Get your free API keyRead the docs
Claude Haiku 5.5Veo 3.1 Lite Text to VideoGPT-6 LunaKling 2.1 StandardNano Banana 2 LiteSeedance 1.0 ProGemini 3.1 Flash LiteFLUX.2 Klein 4B