# Cheapest Vision API Models

As of October 21, 2026, among LiteLLM's active models with a 32K-token context window or more, offered by at least two providers or by their own lab, the cheapest of the vision models is Llama3.2 11B Vision Instruct, at $0.0175 per 1M tokens (blended), from Lambda.

- Page: https://models.litellm.ai/rankings/cheapest-vision-models
- How it's sorted: Sorted by blended price: 3 input tokens for every output token, at each model's headline price (its own lab's API where it sells it, otherwise its cheapest provider). Only models that list image input. Only active models with a 32K-token context window or more, offered by at least two providers or by their own lab. Free models are left out.

| # | Model | Lab | Blended price per 1M tokens | Price per 1M (in / out) | Context | Providers |
|---|---|---|---|---|---|---|
| 1 | [Llama3.2 11B Vision Instruct](https://models.litellm.ai/models/llama-3.2-11b-vision-instruct) | Meta | $0.0175 | $0.015 / $0.025 | 128K | 5 |
| 2 | [Qwen2 VL 7B Instruct](https://models.litellm.ai/models/qwen2-vl-7b-instruct) | Alibaba | $0.03 | $0.02 / $0.06 | 128K | 2 |
| 3 | [Gemma 3 12B IT](https://models.litellm.ai/models/gemma-3-12b-it) | Google | $0.0625 | $0.05 / $0.10 | 128K | 4 |
| 4 | [Ministral 3 3B](https://models.litellm.ai/models/ministral-3-3b) | Mistral AI | $0.10 | $0.10 / $0.10 | 128K | 1 |
| 5 | [Ministral 3 3B Instruct](https://models.litellm.ai/models/ministral-3-3b-instruct) | Mistral AI | $0.10 | $0.10 / $0.10 | 128K | 2 |
| 6 | [Ministral 3B](https://models.litellm.ai/models/ministral-3b) | Mistral AI | $0.10 | $0.10 / $0.10 | 128K | 3 |
| 7 | [Nova Lite](https://models.litellm.ai/models/nova-lite) | Amazon | $0.105 | $0.06 / $0.24 | 300K | 2 |
| 8 | [Nova Lite V1](https://models.litellm.ai/models/nova-lite-v1) | Amazon | $0.105 | $0.06 / $0.24 | 300K | 1 |
| 9 | [Mistral Small 3.2 24B Instruct](https://models.litellm.ai/models/mistral-small-3.2-24b-instruct) | Mistral AI | $0.1062 | $0.075 / $0.20 | 128K | 3 |
| 10 | [Qwen3.5 9B](https://models.litellm.ai/models/qwen3.5-9b) | Alibaba | $0.1125 | $0.10 / $0.15 | 256K | 3 |
| 11 | [GPT-5 Nano](https://models.litellm.ai/models/gpt-5-nano) | OpenAI | $0.1375 | $0.05 / $0.40 | 272K | 7 |
| 12 | [Qwen3.6 35B A3B](https://models.litellm.ai/models/qwen3.6-35b-a3b) | Alibaba | $0.1375 | $0.05 / $0.40 | 256K | 8 |
| 13 | [DeepSeek V4.1 Flash](https://models.litellm.ai/models/deepseek-v4.1-flash) | DeepSeek | $0.1425 | $0.09 / $0.30 | 1M | 14 |
| 14 | [Ministral 3 8B](https://models.litellm.ai/models/ministral-3-8b) | Mistral AI | $0.15 | $0.15 / $0.15 | 256K | 1 |
| 15 | [Ministral 3 8B Instruct](https://models.litellm.ai/models/ministral-3-8b-instruct) | Mistral AI | $0.15 | $0.15 / $0.15 | 128K | 2 |
| 16 | [Ministral 8B](https://models.litellm.ai/models/ministral-8b) | Mistral AI | $0.15 | $0.15 / $0.15 | 256K | 2 |
| 17 | [Mistral Small](https://models.litellm.ai/models/mistral-small) | Mistral AI | $0.15 | $0.10 / $0.30 | 32K | 6 |
| 18 | [Pixtral 12B](https://models.litellm.ai/models/pixtral-12b) | Mistral AI | $0.15 | $0.15 / $0.15 | 128K | 3 |
| 19 | [Gemini 2.5 Flash Lite](https://models.litellm.ai/models/gemini-2.5-flash-lite) | Google | $0.175 | $0.10 / $0.40 | 1M | 3 |
| 20 | [Gemini 2.5 Flash Lite Preview](https://models.litellm.ai/models/gemini-2.5-flash-lite-preview) | Google | $0.175 | $0.10 / $0.40 | 1M | 1 |