Skip to content
Rapid Router
← Every ranking

October 2026

Best cheap AI model

The cheapest models that still rate in the top 40% of LMArena's overall board, sorted by price. Good enough for most work at a fraction of a flagship's cost.

#ModelRatingInput / 1MOutput / 1MContext
1DeepSeek V3.1 TerminusDeepSeek1419$0.060$0.180128K
2DeepSeek V4 FlashDeepSeek1432$0.090$0.1801M
3MiMo-V2.6-FlashDeepinfra1455$0.140$0.2801M
4MiMo-V2.6-FlashNovita1455$0.140$0.2801M
5MiMo-V2.5Xiaomi1428$0.140$0.2801M
6Qwen 3 235b A22B 2507Qwen1419$0.090$0.550262K
7GLM-5.3-FlashZ.ai1471$0.012$0.9001M
8DeepSeek V3.2DeepSeek1425$0.260$0.380164K
9DeepSeek V4.1 FlashDeepinfra1463$0.200$0.6001M
10Qwen3 VL 235B A22B InstructQwen1420$0.200$0.880262K
11DeepSeek-V3.1Deepseek Ai1420$0.250$0.950131K
12GPT 5.6 LunaOpenAI1431$0.200$1.201.1M

Ratings from LMArena, snapshot 2026-10-13, used under its licence with attribution. Prices are what Rapid Router bills per request.

Compare the leaders

How this is ranked

Models are first filtered to the top 40% of LMArena's overall board, then sorted by a blended price of 75% input and 25% output per million tokens, the mix of a typical chat or RAG workload.

Only models that are live and paid on Rapid Router are listed; free-tier and preview models are on the catalog. For your own monthly cost on any of them, use the cost calculator.

Common questions

What is the best cheap ai model?

DeepSeek V3.1 Terminus by DeepSeek ranks first on price among models in the top 40% of LMArena's overall board as of October 2026.

How do I use these models?

Every model here is callable at https://rapidrouter.ai/api/v1 with one Rapid Router key and the OpenAI SDK; switching between them is a one-string change. Each model's page has a ready request.

How often does this ranking change?

It is read from the latest LMArena snapshot (2026-10-13) and the live catalog every time the page loads, so new models and new votes show up without anyone editing the page.

Other rankings: coding · building web apps · hard, multi-step problems · math · writing · following detailed instructions · understanding images · general chat · long documents