# UberLLM

> UberLLM is the market for spare AI capacity. People with unused AI capacity sell it
> below list price; buyers use one OpenAI- and Anthropic-compatible API key that routes
> every request to the cheapest healthy seller for that model (text, image, video, music),
> across 252 models (GPT, Claude, Gemini, DeepSeek, GLM, Qwen,
> Llama, Mistral, Kimi and more). Each request is billed at the price shown: the
> seller's price plus UberLLM's 10% fee, already included. A 5% fee applies when you buy credits.
> Accounts start at $0 and are prepaid. Sign in with an emailed 6-digit code.
> Fastest setup: tell your coding agent "Read https://uberllm.dev/SKILL.md and set me up with UberLLM."

## Use it
- Base URL: https://api.uberllm.dev/v1  (OpenAI-compatible; also /v1/messages for Anthropic SDKs)
- Drop-in: change only the base_url and api_key in the OpenAI or Anthropic SDK.
- Get a key: https://uberllm.dev/signup
- Docs: https://uberllm.dev/docs/quickstart

## Key pages
- [Model market & live prices](https://uberllm.dev/#models)
- [Quickstart](https://uberllm.dev/docs/quickstart)
- [Pricing](https://uberllm.dev/docs/pricing)
- [Sell inference capacity](https://uberllm.dev/sell)
- [LLM API pricing — all models](https://uberllm.dev/llm-api-pricing)
- [Video API pricing — UberLLM vs kie.ai](https://uberllm.dev/video-api-pricing)
- [Cheapest LLM API](https://uberllm.dev/answers/cheapest-llm-api)
- [One API key for all LLMs](https://uberllm.dev/answers/one-api-key-for-all-llms)
- [OpenRouter alternative](https://uberllm.dev/openrouter-alternative)

## Models and best prices (per 1M tokens, input / output)
- DeepSeek V4 Flash (deepseek/deepseek-v4-flash): $0.0718/M in / $0.1436/M out — https://uberllm.dev/models/deepseek/deepseek-v4-flash
- DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash): $0.0491/M in / $0.1965/M out — https://uberllm.dev/models/deepseek/deepseek-v4.1-flash
- Meta: Muse Spark 1.3 (meta-llama/muse-spark-1.3): $0.2316/M in / $0.7873/M out — https://uberllm.dev/models/meta-llama/muse-spark-1.3
- Meta: Muse Spark 1.3 Contributor (meta-llama/muse-spark-1.3-contributor): $0.0208/M in / $0.0416/M out — https://uberllm.dev/models/meta-llama/muse-spark-1.3-contributor
- GPT-6.1 Sol (openai/gpt-6.1-sol): $0.4400/M in / $2.20/M out — https://uberllm.dev/models/openai/gpt-6.1-sol
- GPT-6 Astra (openai/gpt-6-astra): $2.67/M in / $13.33/M out — https://uberllm.dev/models/openai/gpt-6-astra
- Claude Opus 5.5 (anthropic/claude-opus-5.5): $2.51/M in / $12.57/M out — https://uberllm.dev/models/anthropic/claude-opus-5.5
- Claude Sonnet 5.5 (anthropic/claude-sonnet-5.5): $0.9583/M in / $4.79/M out — https://uberllm.dev/models/anthropic/claude-sonnet-5.5
- Meta: Muse Wonder (meta-llama/muse-wonder): $2.19/M in / $10.95/M out — https://uberllm.dev/models/meta-llama/muse-wonder
- GPT-OSS 120B (openai/gpt-oss-120b): $0.0021/M in / $0.0089/M out — https://uberllm.dev/models/openai/gpt-oss-120b
- MiniMax M2.1 (minimax/minimax-m2.1): $0.0005/M in / $0.0018/M out — https://uberllm.dev/models/minimax/minimax-m2.1
- GPT 5 Mini (openai/gpt-5-mini): $0.0267/M in / $0.2134/M out — https://uberllm.dev/models/openai/gpt-5-mini
- Qwen 3 Coder 480B Turbo (qwen/qwen3-coder-turbo): $0.2862/M in / $1.23/M out — https://uberllm.dev/models/qwen/qwen3-coder-turbo
- Qwen3 Next 80B A3B (qwen/qwen3-next-80b-a3b-instruct): $0.0237/M in / $0.2896/M out — https://uberllm.dev/models/qwen/qwen3-next-80b-a3b-instruct
- GPT-5.2 Codex (openai/gpt-5.2-codex): $1.54/M in / $12.31/M out — https://uberllm.dev/models/openai/gpt-5.2-codex
- Llama 3.3 70B Instruct (meta-llama/llama-3.3-70b-instruct): $0.0607/M in / $0.1943/M out — https://uberllm.dev/models/meta-llama/llama-3.3-70b-instruct
- Claude Opus 4.6 (anthropic/claude-opus-4.6): $3.26/M in / $16.31/M out — https://uberllm.dev/models/anthropic/claude-opus-4.6
- Mistral Small 3.2 24B Instruct (mistralai/mistral-small-3.2-24b-instruct): $0.0203/M in / $0.0541/M out — https://uberllm.dev/models/mistralai/mistral-small-3.2-24b-instruct
- Trinity Large Thinking (arcee-ai/trinity-large-thinking): $0.2750/M in / $0.8800/M out — https://uberllm.dev/models/arcee-ai/trinity-large-thinking
- Gemma 4 Uncensored (google/gemma-4-uncensored): $0.1687/M in / $0.5192/M out — https://uberllm.dev/models/google/gemma-4-uncensored
- Qwen 3.6 Plus Uncensored (qwen/qwen3.6-plus-uncensored): $0.5058/M in / $3.03/M out — https://uberllm.dev/models/qwen/qwen3.6-plus-uncensored
- Mistral Small 4 (mistralai/mistral-small-4): $0.1053/M in / $0.4210/M out — https://uberllm.dev/models/mistralai/mistral-small-4
- Claude Haiku 4.5 (anthropic/claude-haiku-4.5): $0.8579/M in / $4.29/M out — https://uberllm.dev/models/anthropic/claude-haiku-4.5
- Qwen3 30B A3B (qwen/qwen3-30b-a3b): $0.0940/M in / $0.3916/M out — https://uberllm.dev/models/qwen/qwen3-30b-a3b
- Kimi K2 Thinking (moonshotai/kimi-k2-thinking): $0.0078/M in / $0.0324/M out — https://uberllm.dev/models/moonshotai/kimi-k2-thinking
- Mistral Large (mistralai/mistral-large): $0.1104/M in / $0.3313/M out — https://uberllm.dev/models/mistralai/mistral-large
- Hermes 3 Llama 3.1 405b (nousresearch/hermes-3-llama-3.1-405b): $0.7858/M in / $0.7858/M out — https://uberllm.dev/models/nousresearch/hermes-3-llama-3.1-405b
- GPT-5.5 Pro (openai/gpt-5.5-pro): $28.54/M in / $171.25/M out — https://uberllm.dev/models/openai/gpt-5.5-pro
- Gemma 3 27B E2EE (google/e2ee-gemma-3-27b): $0.0616/M in / $0.2200/M out — https://uberllm.dev/models/google/e2ee-gemma-3-27b
- Gemini 3.1 Flash Lite (google/gemini-3.1-flash-lite): $0.0917/M in / $0.5503/M out — https://uberllm.dev/models/google/gemini-3.1-flash-lite
- Qwen3.5 Plus (qwen/qwen3.5-plus): $0.2431/M in / $1.46/M out — https://uberllm.dev/models/qwen/qwen3.5-plus
- GPT-5.4 (openai/gpt-5.4): $0.3072/M in / $1.84/M out — https://uberllm.dev/models/openai/gpt-5.4
- GPT-5.4 Pro (openai/gpt-5.4-pro): $24.99/M in / $149.97/M out — https://uberllm.dev/models/openai/gpt-5.4-pro
- GPT-5.4 Mini (openai/gpt-5.4-mini): $0.1145/M in / $0.6871/M out — https://uberllm.dev/models/openai/gpt-5.4-mini
- GPT-5.5 (openai/gpt-5.5): $1.24/M in / $7.42/M out — https://uberllm.dev/models/openai/gpt-5.5
- GPT-5.3 Codex (openai/gpt-5.3-codex): $0.2628/M in / $2.10/M out — https://uberllm.dev/models/openai/gpt-5.3-codex
- Claude Sonnet 4.5 (anthropic/claude-sonnet-4.5): $1.67/M in / $8.35/M out — https://uberllm.dev/models/anthropic/claude-sonnet-4.5
- Kimi K2.6 (moonshotai/kimi-k2.6): $0.1658/M in / $0.8699/M out — https://uberllm.dev/models/moonshotai/kimi-k2.6
- GPT OSS 20B (openai/e2ee-gpt-oss-20b-p): $0.0275/M in / $0.1045/M out — https://uberllm.dev/models/openai/e2ee-gpt-oss-20b-p
- NVIDIA Nemotron 3 Nano 30B (nvidia/nemotron-3-nano-30b-a3b): $0.0012/M in / $0.0047/M out — https://uberllm.dev/models/nvidia/nemotron-3-nano-30b-a3b
- Qwen 3 235B A22B Instruct 2507 (qwen/qwen3-235b-a22b-2507): $0.0013/M in / $0.0082/M out — https://uberllm.dev/models/qwen/qwen3-235b-a22b-2507
- GLM 5V Turbo (z-ai/glm-5v-turbo): $1.01/M in / $3.38/M out — https://uberllm.dev/models/z-ai/glm-5v-turbo
- Gemini 2.5 Pro (google/gemini-2.5-pro): $0.4649/M in / $3.72/M out — https://uberllm.dev/models/google/gemini-2.5-pro
- Mercury 2 (inception/mercury-2): $0.2750/M in / $0.8250/M out — https://uberllm.dev/models/inception/mercury-2
- GPT 5.4 Nano (openai/gpt-5.4-nano): $0.0453/M in / $0.2830/M out — https://uberllm.dev/models/openai/gpt-5.4-nano
- Gemma 3 27B (google/gemma-3-27b-it): $0.0010/M in / $0.0026/M out — https://uberllm.dev/models/google/gemma-3-27b-it
- Gemini 3.1 Pro (google/gemini-3.1-pro): $1.98/M in / $11.88/M out — https://uberllm.dev/models/google/gemini-3.1-pro
- Qwen 2.5 7B (qwen/e2ee-qwen-2-5-7b-p): $0.0337/M in / $0.0877/M out — https://uberllm.dev/models/qwen/e2ee-qwen-2-5-7b-p
- Qwen 3 Coder 480b (qwen/qwen3-coder): $0.0126/M in / $0.0419/M out — https://uberllm.dev/models/qwen/qwen3-coder
- Kimi K2 (moonshotai/kimi-k2): $0.4640/M in / $1.87/M out — https://uberllm.dev/models/moonshotai/kimi-k2
- Gemini 2.5 Flash (google/gemini-2.5-flash): $0.0080/M in / $0.0668/M out — https://uberllm.dev/models/google/gemini-2.5-flash
- GPT OSS 120B (openai/e2ee-gpt-oss-120b-p): $0.1041/M in / $0.5206/M out — https://uberllm.dev/models/openai/e2ee-gpt-oss-120b-p
- Claude Opus 4.7 (anthropic/claude-opus-4.7): $0.6166/M in / $3.08/M out — https://uberllm.dev/models/anthropic/claude-opus-4.7
- Qwen 3.5 9B (qwen/qwen3.5-9b): $0.0880/M in / $0.1320/M out — https://uberllm.dev/models/qwen/qwen3.5-9b
- Grok 4.20 Multi-Agent Beta (x-ai/grok-4.20-multi-agent-beta): $0.8059/M in / $1.61/M out — https://uberllm.dev/models/x-ai/grok-4.20-multi-agent-beta
- MiniMax M2.7 Highspeed (minimax/minimax-m2.7-highspeed): $0.5940/M in / $2.38/M out — https://uberllm.dev/models/minimax/minimax-m2.7-highspeed
- Llama 3.2 3B (meta-llama/llama-3.2-3b-instruct): $0.0484/M in / $0.3189/M out — https://uberllm.dev/models/meta-llama/llama-3.2-3b-instruct
- Qwen 3.6 27B (qwen/qwen3.6-27b): $0.1287/M in / $1.03/M out — https://uberllm.dev/models/qwen/qwen3.6-27b
- GLM 4.7 Flash Heretic (z-ai/glm-4.7-flash-heretic): $0.0550/M in / $0.3145/M out — https://uberllm.dev/models/z-ai/glm-4.7-flash-heretic
- Venice Uncensored 1.2 (venice/uncensored-1.2): $0.1532/M in / $0.6892/M out — https://uberllm.dev/models/venice/uncensored-1.2

Full catalog (252 models): https://uberllm.dev/#models