Live · updated 6 hr ago 352 Models Tracked

The LLM Price Index

Every major large language model, normalized to dollars per million tokens. Scored on value, cheapness, and frontier capability. Independent, automated, refreshed daily.

Models 352
Providers 20+
Free Tier Models 27
Median Price / Mtok $0.700

What this is

The LLM Price Index is a live, independently maintained price comparison for every large language model offered through the OpenRouter catalog. Input and output pricing is normalized to dollars per million tokens, blended 3:1 to produce a single comparable figure, and scored 0–10 on three axes: value, cheapness, and frontier capability. The cheapest paid model right now is Ling-2.6-flash at $0.015 per million tokens (3:1 blended).

Lyria 3 Pro Preview

9.0/10
Google · google/lyria-3-pro-preview
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API.…

10.0Value
10.0Cheap
6.5Frontier
Audio Free 1.0M ctx Vision

Lyria 3 Clip Preview

9.0/10
Google · google/lyria-3-clip-preview
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the…

10.0Value
10.0Cheap
6.5Frontier
Audio Free 1.0M ctx Vision

Owl Alpha

9.0/10
OpenRouter · openrouter/owl-alpha
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in…

10.0Value
10.0Cheap
6.5Frontier
Text Free 1.0M ctx Tools

DeepSeek V4 Flash (free)

9.0/10
DeepSeek · deepseek/deepseek-v4-flash:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context…

10.0Value
10.0Cheap
6.5Frontier
Text Free Open weights 1.0M ctx Tools Reasoning

Gemma 4 26B A4B (free)

8.7/10
Google · google/gemma-4-26b-a4b-it:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per…

10.0Value
10.0Cheap
5.5Frontier
Vision Free Open weights 262K ctx Tools Reasoning

Gemma 4 31B (free)

8.7/10
Google · google/gemma-4-31b-it:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K…

10.0Value
10.0Cheap
5.5Frontier
Vision Free Open weights 262K ctx Tools Reasoning

Nemotron 3 Nano Omni (free)

8.7/10
NVIDIA · nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise…

10.0Value
10.0Cheap
5.5Frontier
Audio Free 256K ctx Vision Tools Reasoning

Laguna XS.2 (free)

8.7/10
Poolside · poolside/laguna-xs.2:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling…

10.0Value
10.0Cheap
5.5Frontier
Reasoning Free Open weights 262K ctx Tools

Laguna M.1 (free)

8.7/10
Poolside · poolside/laguna-m.1:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it…

10.0Value
10.0Cheap
5.5Frontier
Reasoning Free 262K ctx Tools

Kimi K2.6 (free)

8.7/10
Moonshotai · moonshotai/kimi-k2.6:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end…

10.0Value
10.0Cheap
5.5Frontier
Vision Free Open weights 262K ctx Tools Reasoning

Ling-2.6-flash

8.5/10
Inclusionai · inclusionai/ling-2.6-flash
$0.010 Input /Mtok
$0.030 Output /Mtok
$0.015 Blended 3:1

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require…

10.0Value
9.7Cheap
5.5Frontier
Text 262K ctx Tools #1 cheapest

Nemotron 3 Super (free)

8.5/10
NVIDIA · nvidia/nemotron-3-super-120b-a12b:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in…

10.0Value
10.0Cheap
5.0Frontier
Text Free Open weights 1.0M ctx Tools Reasoning

MiniMax M2.5 (free)

8.2/10
Minimax · minimax/minimax-m2.5:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments,…

10.0Value
10.0Cheap
4.0Frontier
Text Free Open weights 262K ctx Tools Reasoning

Free Models Router

8.2/10
OpenRouter · openrouter/free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on…

10.0Value
10.0Cheap
4.0Frontier
Vision Free 200K ctx Tools Reasoning

Nemotron 3 Nano 30B A3B (free)

8.2/10
NVIDIA · nvidia/nemotron-3-nano-30b-a3b:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build…

10.0Value
10.0Cheap
4.0Frontier
Text Free Open weights 256K ctx Tools Reasoning

Qwen3 Coder 480B A35B (free)

8.2/10
Qwen · qwen/qwen3-coder:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as…

10.0Value
10.0Cheap
4.0Frontier
Code Free Open weights 1.0M ctx Tools

DeepSeek V4 Flash

8.2/10
DeepSeek · deepseek/deepseek-v4-flash
$0.100 Input /Mtok
$0.200 Output /Mtok
$0.125 Blended 3:1

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context…

10.0Value
7.8Cheap
6.5Frontier
Text Open weights 1.0M ctx Tools Reasoning #40 cheapest

MiMo-V2.5

8.1/10
Xiaomi · xiaomi/mimo-v2.5
$0.140 Input /Mtok
$0.280 Output /Mtok
$0.175 Blended 3:1

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni…

10.0Value
7.5Cheap
6.5Frontier
Audio Open weights 1.0M ctx Vision Tools Reasoning

Granite 4.1 8B

7.9/10
Ibm Granite · ibm-granite/granite-4.1-8b
$0.050 Input /Mtok
$0.100 Output /Mtok
$0.063 Blended 3:1

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token…

10.0Value
8.4Cheap
5.0Frontier
Text Open weights 131K ctx Tools #15 cheapest

Hy3 preview

7.9/10
Tencent · tencent/hy3-preview
$0.066 Input /Mtok
$0.260 Output /Mtok
$0.115 Blended 3:1

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across…

10.0Value
7.9Cheap
5.5Frontier
Reasoning Open weights 262K ctx Tools #33 cheapest

Qwen3 Next 80B A3B Instruct (free)

7.9/10
Qwen · qwen/qwen3-next-80b-a3b-instruct:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks…

10.0Value
10.0Cheap
3.0Frontier
Reasoning Free Open weights 262K ctx Tools

Gemma 4 26B A4B

7.9/10
Google · google/gemma-4-26b-a4b-it
$0.060 Input /Mtok
$0.330 Output /Mtok
$0.128 Blended 3:1

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per…

10.0Value
7.8Cheap
5.5Frontier
Vision Open weights 262K ctx Tools Reasoning #41 cheapest

Qwen3.6 Flash

7.8/10
Qwen · qwen/qwen3.6-flash
$0.188 Input /Mtok
$1.13 Output /Mtok
$0.422 Blended 3:1

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a…

10.0Value
6.8Cheap
6.5Frontier
Vision 1.0M ctx Tools Reasoning

Gemma 4 31B

7.8/10
Google · google/gemma-4-31b-it
$0.120 Input /Mtok
$0.370 Output /Mtok
$0.183 Blended 3:1

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K…

10.0Value
7.5Cheap
5.5Frontier
Vision Open weights 262K ctx Tools Reasoning

Qwen3.5-Flash

7.8/10
Qwen · qwen/qwen3.5-flash-02-23
$0.065 Input /Mtok
$0.260 Output /Mtok
$0.114 Blended 3:1

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts…

10.0Value
7.9Cheap
5.0Frontier
Vision 1.0M ctx Tools Reasoning #32 cheapest

LFM2.5-1.2B-Thinking (free)

7.8/10
Liquid · liquid/lfm-2.5-1.2b-thinking:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports…

10.0Value
10.0Cheap
2.5Frontier
Reasoning Free Open weights 33K ctx

LFM2.5-1.2B-Instruct (free)

7.8/10
Liquid · liquid/lfm-2.5-1.2b-instruct:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint,…

10.0Value
10.0Cheap
2.5Frontier
Text Free Open weights 33K ctx

Nemotron Nano 12B 2 VL (free)

7.8/10
NVIDIA · nvidia/nemotron-nano-12b-v2-vl:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a…

10.0Value
10.0Cheap
2.5Frontier
Vision Free Open weights 128K ctx Tools Reasoning

Nemotron Nano 9B V2 (free)

7.8/10
NVIDIA · nvidia/nemotron-nano-9b-v2:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and…

10.0Value
10.0Cheap
2.5Frontier
Reasoning Free Open weights 128K ctx Tools

gpt-oss-120b (free)

7.8/10
OpenAI · openai/gpt-oss-120b:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates…

10.0Value
10.0Cheap
2.5Frontier
Reasoning Free Open weights 131K ctx Tools

gpt-oss-20b (free)

7.8/10
OpenAI · openai/gpt-oss-20b:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with…

10.0Value
10.0Cheap
2.5Frontier
Text Free Open weights 131K ctx Tools Reasoning

GLM 4.5 Air (free)

7.8/10
Z Ai · z-ai/glm-4.5-air:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts…

10.0Value
10.0Cheap
2.5Frontier
Text Free Open weights 131K ctx Tools Reasoning

Gemini 3.1 Flash Lite

7.7/10
Google · google/gemini-3.1-flash-lite
$0.250 Input /Mtok
$1.50 Output /Mtok
$0.563 Blended 3:1

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and…

10.0Value
6.5Cheap
6.5Frontier
Audio 1.0M ctx Vision Tools Reasoning

Qwen3.5 Plus 2026-04-20

7.7/10
Qwen · qwen/qwen3.5-plus-20260420
$0.300 Input /Mtok
$1.80 Output /Mtok
$0.675 Blended 3:1

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text…

10.0Value
6.3Cheap
6.5Frontier
Vision 1.0M ctx Tools Reasoning

Qwen3.6 Plus

7.7/10
Qwen · qwen/qwen3.6-plus
$0.325 Input /Mtok
$1.95 Output /Mtok
$0.731 Blended 3:1

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance…

10.0Value
6.3Cheap
6.5Frontier
Vision 1.0M ctx Tools Reasoning

Nemotron 3 Super

7.6/10
NVIDIA · nvidia/nemotron-3-super-120b-a12b
$0.090 Input /Mtok
$0.450 Output /Mtok
$0.180 Blended 3:1

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in…

10.0Value
7.5Cheap
5.0Frontier
Text Open weights 1.0M ctx Tools Reasoning

Qwen3.5-9B

7.6/10
Qwen · qwen/qwen3.5-9b
$0.040 Input /Mtok
$0.150 Output /Mtok
$0.068 Blended 3:1

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient…

10.0Value
8.3Cheap
4.0Frontier
Vision Open weights 262K ctx Tools Reasoning #17 cheapest

MiMo-V2.5-Pro

7.6/10
Xiaomi · xiaomi/mimo-v2.5-pro
$0.435 Input /Mtok
$0.870 Output /Mtok
$0.544 Blended 3:1

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on…

9.7Value
6.5Cheap
6.5Frontier
Text Open weights 1.0M ctx Tools Reasoning

DeepSeek V4 Pro

7.6/10
DeepSeek · deepseek/deepseek-v4-pro
$0.435 Input /Mtok
$0.870 Output /Mtok
$0.544 Blended 3:1

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context…

9.7Value
6.5Cheap
6.5Frontier
Reasoning Open weights 1.0M ctx Tools

Ling-2.6-1T

7.6/10
Inclusionai · inclusionai/ling-2.6-1t
$0.075 Input /Mtok
$0.625 Output /Mtok
$0.213 Blended 3:1

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and…

9.6Value
7.4Cheap
5.5Frontier
Text 262K ctx Tools

Qwen3.6 35B A3B

7.6/10
Qwen · qwen/qwen3.6-35b-a3b
$0.140 Input /Mtok
$1.00 Output /Mtok
$0.355 Blended 3:1

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It…

10.0Value
6.9Cheap
5.5Frontier
Vision Open weights 262K ctx Tools Reasoning

Nemotron 3 Nano 30B A3B

7.5/10
NVIDIA · nvidia/nemotron-3-nano-30b-a3b
$0.050 Input /Mtok
$0.200 Output /Mtok
$0.088 Blended 3:1

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build…

10.0Value
8.1Cheap
4.0Frontier
Text Open weights 262K ctx Tools Reasoning #25 cheapest

Trinity Mini

7.5/10
Arcee Ai · arcee-ai/trinity-mini
$0.045 Input /Mtok
$0.150 Output /Mtok
$0.071 Blended 3:1

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient…

10.0Value
8.3Cheap
3.5Frontier
Reasoning Open weights 131K ctx Tools #20 cheapest

Uncensored (free)

7.5/10
Cognitivecomputations · cognitivecomputations/dolphin-mistral-24b-venice-edition:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model…

10.0Value
10.0Cheap
1.5Frontier
Text Free Open weights 33K ctx

Llama 3.3 70B Instruct (free)

7.5/10
Meta · meta-llama/llama-3.3-70b-instruct:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).…

10.0Value
10.0Cheap
1.5Frontier
Text Free Open weights 131K ctx Tools

Llama 3.2 3B Instruct (free)

7.5/10
Meta · meta-llama/llama-3.2-3b-instruct:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and…

10.0Value
10.0Cheap
1.5Frontier
Reasoning Free Open weights 131K ctx

Hermes 3 405B Instruct (free)

7.5/10
Nous Research · nousresearch/hermes-3-llama-3.1-405b:free
Free Input /Mtok
Free Output /Mtok
Free Blended 3:1

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn…

10.0Value
10.0Cheap
1.5Frontier
Reasoning Free Open weights 131K ctx

Seed 1.6 Flash

7.4/10
Bytedance Seed · bytedance-seed/seed-1.6-flash
$0.075 Input /Mtok
$0.300 Output /Mtok
$0.131 Blended 3:1

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a…

10.0Value
7.8Cheap
4.0Frontier
Vision 262K ctx Tools Reasoning #44 cheapest

Free · No spam

Price drops, new models, deprecations

Every Tuesday: which models got cheaper, which launched, which got pulled. Five minutes. No filler.

Three axes, one overall score

  • Value (35%) — capability per dollar. Context length, vision, tools, and structured-output support divided by log-scaled blended price.
  • Cheapness (35%) — raw affordability. Free models score 10. Paid models use an inverse log curve anchored at $0.01 / Mtok.
  • Frontier (30%) — how close to the state of the art. Recent releases, long context windows, and premium pricing all contribute.

Blended price formula

  • Most production workloads are input-heavy, so the index uses a 3:1 blended price: (input × 0.75) + (output × 0.25).
  • All prices are normalized to dollars per million tokens. OpenRouter publishes per-token figures which we multiply by 1,000,000 before display.

Where does the pricing data come from?

Every model and price on this page is sourced from OpenRouter's public models API, which aggregates pricing directly from model providers including Anthropic, OpenAI, Google, Mistral, Meta, xAI, DeepSeek, and dozens of others. The pipeline re-fetches and re-scores the entire catalog once per day.

Why normalize to $/million tokens?

Model providers publish prices in inconsistent units — per 1K tokens, per million tokens, per character, sometimes per request. Comparing them directly is error-prone. Dollars per million tokens is the industry's most common reporting unit and makes cross-provider comparisons immediate and honest.

What does "3:1 blended" mean?

Most production LLM workloads are input-heavy — context, RAG retrievals, system prompts — while output is comparatively short. A 3:1 input:output ratio is the informal industry convention for producing a single number that reflects typical cost: (input × 0.75) + (output × 0.25). Your actual ratio may differ; always check both input and output columns for workloads with long generations.

What's the cheapest LLM right now?

The cheapest paid model as of the latest scan is Ling-2.6-flash from Inclusionai at $0.015 per million tokens (3:1 blended). Sort by "Cheapest" above for the full ranking. Many providers also offer free-tier variants of their models, which score a perfect 10 on the cheapness axis.

Is this affiliated with OpenRouter or any provider?

No. MegaOne AI is independent. OpenRouter is used as a public data source because their models API is the most complete and up-to-date LLM catalog available, but this directory is not operated by OpenRouter and we rate all models — including ones that compete with one another.

How often does the price index update?

A full re-fetch, re-score, and daily snapshot runs once per 24 hours. Snapshots are written to a history table so we can build price-over-time charts and detect drops. New models typically appear within 24 hours of being added to OpenRouter.

Is it free to use?

Yes. Browsing, filtering, sorting, and searching the entire price index is free. The weekly email briefing is free. There is no account required and no paywall.