Cheapest AI models by API
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on October 14, 2026· 221 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 10/14/2026.
| # | Model | Provider | Input $/1M | Output $/1M | Context | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| 1 | Lyria 3 Clip Preview | $0.000 | $0.000 | 1 M | 03/25/2026 | ||
| 2 | Lyria 3 Pro Preview | $0.000 | $0.000 | 1 M | 03/25/2026 | ||
| 3 | DeepSeek V4 Flash 0731 | DeepSeek | $0.016 | $0.640 | 1 M | 07/31/2026 | |
| 4 | DeepSeek V4.1 Flash | DeepSeek | $0.021 | $0.891 | 1 M | 09/10/2026 | |
| 5 | Qwen3.7 Flash | Qwen | $0.030 | $0.130 | 1 M | 07/15/2026 | |
| 6 | Qwen3.8 27B | Qwen | $0.040 | $2.30 | 1 M | 08/14/2026 | |
| 7 | Qwen3.5-Flash | Qwen | $0.065 | $0.260 | 1 M | 02/25/2026 | |
| 8 | gpt-oss-safeguard-20b | OpenAI | $0.075 | $0.300 | 131 K | 10/29/2025 | |
| 9 | Gemma 4 26B A4B | $0.090 | $0.300 | 262 K | 04/02/2026 | ||
| 10 | Gemma 4 31B | $0.090 | $0.340 | 262 K | 04/02/2026 | ||
| 11 | DeepSeek V4 Flash 0423 | DeepSeek | $0.091 | $0.182 | 1 M | 04/24/2026 | |
| 12 | Ministral 3 3B 2512 | Mistral | $0.100 | $0.100 | 131 K | 12/02/2025 | |
| 13 | Qwen3.5-9B | Qwen | $0.100 | $0.150 | 262 K | 02/23/2026 | |
| 14 | Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | 1 M | 10/07/2026 | |
| 15 | GPT-6 Luna Pro | OpenAI | $0.100 | $0.500 | 1.1 M | 09/22/2026 | |
| 16 | GPT-6 Luna | OpenAI | $0.100 | $0.500 | 1.1 M | 09/22/2026 | |
| 17 | Qwen3.6 35B A3B | Qwen | $0.100 | $0.950 | 262 K | 04/17/2026 | |
| 18 | Qwen3 VL 32B Instruct | Qwen | $0.104 | $0.416 | 131 K | 10/23/2025 | |
| 19 | Qwen3 Coder Next | Qwen | $0.120 | $0.800 | 262 K | 02/03/2026 | |
| 20 | Ministral 3 8B 2512 | Mistral | $0.150 | $0.150 | 262 K | 12/02/2025 | |
| 21 | Qwen3.8 Omni Flash | Qwen | $0.150 | $0.470 | 1 M | 09/17/2026 | |
| 22 | Qwen3.8 Flash | Qwen | $0.150 | $0.470 | 1 M | 08/26/2026 | |
| 23 | Mistral Small 4 | Mistral | $0.150 | $0.600 | 262 K | 03/16/2026 | |
| 24 | Qwen3.5-35B-A3B | Qwen | $0.150 | $1.00 | 262 K | 02/23/2026 | |
| 25 | Qwen3 VL 8B Thinking | Qwen | $0.180 | $2.10 | 131 K | 10/14/2025 |
Frequently asked questions
What is the cheapest AI model by API?
Lyria 3 Clip Preview, by Google: $0.000 per million input tokens and $0.000 output, as of 10/14/2026.
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.