100000104Fit score
Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...
Model details →Cheapest AI models per token
Sorted by lowest input-token price. Output prices vary; check the per-model page for full pricing.
100000104Fit score
The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...
Model details →100000104Fit score
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
Model details →Top 25 models for cheap APIs
| # | Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|---|
| 1 | NVIDIA: Switchyard | Nvidia | 1M Ultra context (1M+) | $-1000000.00 | Budget |
| 2 | Auto Router | Openrouter | 2M Ultra context (1M+) | $-1000000.00 | Budget |
| 3 | Auto Router (Beta) | Openrouter | 2M Ultra context (1M+) | $-1000000.00 | Budget |
| 4 | OpenRouter: Fusion | Openrouter | 1M Ultra context (1M+) | $-1000000.00 | Budget |
| 5 | Pareto Code Router | Openrouter | 2M Ultra context (1M+) | $-1000000.00 | Budget |
| 6 | TypeSafe: Jev Router | Typesafe | 1M Ultra context (1M+) | $-1000000.00 | Budget |
| 7 | Body Builder (beta) | Openrouter | 128K Long context (128K+) | $-1000000.00 | Budget |
| 8 | DeepSeek: DeepSeek V4 Flash 0731 (free) | DeepSeek | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 9 | Google: Lyria 3 Clip Preview | 1.0M Ultra context (1M+) | $0.00 | Budget | |
| 10 | Google: Lyria 3 Pro Preview | 1.0M Ultra context (1M+) | $0.00 | Budget | |
| 11 | MiniMax: MiniMax M3 (free) | Minimax | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 12 | NVIDIA: Nemotron 3 Ultra (free) | Nvidia | 1M Ultra context (1M+) | $0.00 | Budget |
| 13 | NVIDIA: Nemotron 3.5 Lightning (free) | Nvidia | 1M Ultra context (1M+) | $0.00 | Budget |
| 14 | Qwen: Qwen3.6 Plus Preview (free) | Qwen | 1M Ultra context (1M+) | $0.00 | Budget |
| 15 | Ox Alpha | Stealth | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 16 | Space Bunny Alpha | Stealth | 1M Ultra context (1M+) | $0.00 | Budget |
| 17 | Thinking Machines: Inkling (free) | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 18 | Thinking Machines: Inkling Small (free) | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 19 | Apodex: Apodex 1.1 Mini (free) | Apodex | 262K Long context (128K+) | $0.00 | Budget |
| 20 | Cohere: North Mini Code (free) | Cohere | 256K Long context (128K+) | $0.00 | Budget |
| 21 | Dots Studio: Dots3-Note Preview (free) | Dots Studio | 512K Long context (128K+) | $0.00 | Budget |
| 22 | Google: Gemma 4 26B A4B (free) | 262K Long context (128K+) | $0.00 | Budget | |
| 23 | Google: Gemma 4 31B (free) | 262K Long context (128K+) | $0.00 | Budget | |
| 24 | inclusionAI: Ling 3.0 Flash Fin (free) | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
| 25 | inclusionAI: Ling 3.0 Flash Sante (free) | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
Frequently asked questions
How is price per million tokens calculated?
Most providers price input and output tokens separately. The number on this page is input price; output is typically 2–5× higher.
Related use cases
AI models for codingAI reasoning modelsAI vision modelslong-context AI models (128K+)AI models for function callingAI models for structured / JSON outputsAI models for agentsfree AI modelsmultilingual AI modelsembedding modelssmall / on-device AI modelsAI image generation modelsAI voice / audio modelsAI models for mathAI models for writingopen-source AI modelsAI models for RAGAI models for summarizationAI models for translationAI models for enterprise