LLM Price Index
As of October 24, 2026
What AI models actually cost today, across every provider you can reach through one UberLLM key. Every figure is read live from the public catalog and includes UberLLM’s 10% fee — nothing is estimated, and anything that can’t be derived from the live catalog is left out.
As of October 24, 2026, the cheapest LLM API on UberLLM is Qwen: Qwen3.8 Omni Flash at $0.0005 per 1M tokens blended ($0.0002 in / $0.0005 out). The cheapest image API is Flux 2 Pro (Venice) at $0.0026 per image. The cheapest video API is Seedance 2.0 (image-to-video) at $0.029 per video. The cheapest music API is MMAudio V2 Text-to-Audio (Venice) at $0.0072 per track.
Cheapest LLM APIs
Ranked by blended cost per 1M tokens (input weighted 1, output 3), cheapest first.
| # | Model | Input / 1M | Output / 1M | Blended / 1M |
|---|---|---|---|---|
| 1 | Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.0002 | $0.0005 | $0.0005 |
| 2 | Gemma 3 4B IT google/gemma-3-4b-it | $0.0005 | $0.0007 | $0.0006 |
| 3 | GPT-OSS 20B openai/gpt-oss-20b | $0.0002 | $0.0009 | $0.0007 |
| 4 | Ministral 3B mistralai/ministral-3-3b-instruct | $0.0011 | $0.0011 | $0.0011 |
| 5 | MiniMax M2.5 minimax/minimax-m2.5 | $0.0004 | $0.0015 | $0.0012 |
| 6 | DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.0000 | $0.0017 | $0.0013 |
| 7 | MiniMax M2.1 minimax/minimax-m2.1 | $0.0004 | $0.0016 | $0.0013 |
| 8 | Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.0005 | $0.0016 | $0.0013 |
| 9 | Gemma 3 12B IT google/gemma-3-12b-it | $0.0005 | $0.0016 | $0.0014 |
| 10 | DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.0010 | $0.0020 | $0.0018 |
Cheapest image, video & music APIs
Cheapest image API $0.0026 per image
Priced per image (or per megapixel).
- Flux 2 Pro (Venice)$0.0026 per image
- Seedream 4.5$0.0026 per image
- FLUX.2 Klein 4B$0.0041 per megapixel
- Z-Image Turbo (Venice)$0.0044 per image
- Lustify SDXL (Venice)$0.0055 per image
Cheapest video API $0.029 per video
Priced per video, or per second for resolution-based models.
- Seedance 2.0 (image-to-video)$0.029 per video
- Ovi Image-to-Video$0.0315 per video
- Wan 2.6 Flash Image-to-Video$0.0431 per video
- Grok Imagine Reference To Video Private (reference-to-video)$0.0462 per video
- Grok Imagine Image To Video Private (image-to-video)$0.0462 per video
Cheapest music API $0.0072 per track
Priced per track or job.
- MMAudio V2 Text-to-Audio (Venice)$0.0072 per track
- ElevenLabs Sound Effects v2 (Venice)$0.011 per track
- ACE-Step 1.5 (Venice)$0.0264 per track
- MiniMax Music 2.0 (Venice)$0.0286 per track
- ElevenLabs TTS Multilingual v2 (Venice audio)$0.066 per track
Biggest live discounts
How far today’s cheapest route sits below each model’s list price, deepest first.
| Model | % off list | Price now |
|---|---|---|
| Text-to-Video Standard (Uncensored AI) uncensored/uncensored-t2v-standard | 100% | $0.18 per video |
| Text-to-Video Turbo (Uncensored AI) uncensored/uncensored-t2v-turbo | 100% | $0.0924 per video |
| Seedance 2.0 Fast Text-to-Video (Uncensored AI) uncensored/uncensored-seedance-2-0-fast-t2v | 100% | $0.15 per video |
| AV-Gen Text-to-Video (Uncensored AI) uncensored/uncensored-av-gen | 100% | $0.15 per video |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | 99.9% | $0.0048 / 1M blended |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | 99.9% | $0.0058 / 1M blended |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | 99.9% | $0.0005 / 1M blended |
| MiniMax M2.1 minimax/minimax-m2.1 | 99.9% | $0.0013 / 1M blended |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | 99.9% | $0.0042 / 1M blended |
| MiniMax M2.5 minimax/minimax-m2.5 | 99.9% | $0.0012 / 1M blended |
Cheapest model in every family
The lowest blended $/1M-token model in each family, cheapest family first — 49 families.
Source: UberLLM public models catalog, read live at https://api.uberllm.dev/api/v1/public/models. Blended price weights input and output 1:3 and includes UberLLM’s 10% fee. Media prices are per unit in each model’s own unit. No historical trend is shown because no price history series is published.
LLM Price Index — FAQ
What is the cheapest LLM API right now?
This report ranks every model you can call through UberLLM by blended cost per million tokens (input weighted 1, output 3) and lists the cheapest first, as of October 24, 2026. Prices are read live from the cross-provider catalog and include UberLLM’s 10% fee, so the price shown is the price paid.
Where does this pricing data come from?
Every number is derived from UberLLM’s public models catalog (https://api.uberllm.dev/api/v1/public/models), the same live feed that powers the marketplace. There is no estimation and no historical back-fill: the page states what models cost on the day it is read, and omits any figure it cannot derive from the live catalog.
How often is the LLM Price Index updated?
Continuously. The page is generated per request from the live catalog and dated to the day you read it, so a citation of "the cheapest LLM API as of <date>" reflects the market on that date.