Cheapest AI models by API

Pick up to 3 models · pricing, context and capabilities · simulate your product cost

Data updated on September 30, 2026· 217 models

The 25 cheapest chat models by API, sorted by input price per million tokens (output price breaks ties). Only models released in the last 12 months. Data as of 09/30/2026.

#ModelProviderInput $/1MOutput $/1MContextCapabilitiesReleased
1Lyria 3 Pro PreviewGoogle$0.000$0.0001 M03/25/2026
2Lyria 3 Clip PreviewGoogle$0.000$0.0001 M03/25/2026
3DeepSeek V4 Flash 0731DeepSeek$0.018$0.3201 M07/31/2026
4Qwen3.7 FlashQwen$0.030$0.1301 M07/15/2026
5Qwen3.5-FlashQwen$0.065$0.2601 M02/25/2026
6gpt-oss-safeguard-20bOpenAI$0.075$0.300131 K10/29/2025
7Gemma 4 26B A4B Google$0.077$0.255262 K04/02/2026
8Gemma 4 31BGoogle$0.090$0.340262 K04/02/2026
9Ministral 3 3B 2512Mistral$0.100$0.100131 K12/03/2025
10Qwen3.5-9BQwen$0.100$0.150262 K02/23/2026
11GPT-6 LunaOpenAI$0.100$0.5001.1 M09/22/2026
12GPT-6 Luna ProOpenAI$0.100$0.5001.1 M09/22/2026
13Qwen3 VL 32B InstructQwen$0.104$0.416131 K10/23/2025
14Qwen3 VL 8B InstructQwen$0.117$0.455262 K10/14/2025
15Qwen3 Coder NextQwen$0.120$0.800262 K02/03/2026
16DeepSeek V4 Flash 0423DeepSeek$0.140$0.2801 M04/24/2026
17Ministral 3 8B 2512Mistral$0.150$0.150262 K12/03/2025
18Qwen3.8 Omni FlashQwen$0.150$0.4701 M09/17/2026
19Qwen3.8 FlashQwen$0.150$0.4701 M08/26/2026
20Mistral Small 4Mistral$0.150$0.600262 K03/16/2026
21Qwen3 VL 30B A3B InstructQwen$0.150$0.600262 K10/02/2025
22Qwen3.6 35B A3BQwen$0.150$1.00262 K04/17/2026
23Qwen3.5-35B-A3BQwen$0.163$1.30262 K02/23/2026
24Qwen3 VL 8B ThinkingQwen$0.180$2.10131 K10/14/2025
25Qwen3.6 FlashQwen$0.188$1.131 M04/27/2026

Frequently asked questions

What is the cheapest AI model by API?

Lyria 3 Pro Preview, by Google: $0.000 per million input tokens and $0.000 output, as of 09/30/2026.

How is this list sorted?

By input price per million tokens, lowest first; ties by output price. Only chat models released in the last 12 months (25 in total).

Where do the prices come from and how often are they updated?

From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.

What does price per million tokens mean?

It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.

Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.