# AI Models Under $1 per 1M Tokens

As of October 21, 2026, 178 of LiteLLM's active models with a 32K-token context window or more, offered by at least two providers or by their own lab, cost under $1 per 1M tokens (blended). The most widely offered is GPT OSS 120B, from 24 providers, at $0.065 per 1M tokens.

- Page: https://models.litellm.ai/rankings/models-under-1-dollar
- How it's sorted: Models whose blended price (3 input tokens per output token, at the headline price) is under $1.00, sorted by how many providers offer them through LiteLLM, then by price. 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 | Providers on LiteLLM | Price per 1M (in / out) | Context | Providers |
|---|---|---|---|---|---|---|
| 1 | [GPT OSS 120B](https://models.litellm.ai/models/gpt-oss-120b) | OpenAI | 24 providers | $0.03 / $0.17 | 131K | 24 |
| 2 | [DeepSeek V4 Flash](https://models.litellm.ai/models/deepseek-v4-flash) | DeepSeek | 23 providers | $0.30 / $1.20 | 1M | 23 |
| 3 | [Llama 3.3 70B Instruct](https://models.litellm.ai/models/llama-3.3-70b-instruct) | Meta | 19 providers | $0.12 / $0.30 | 128K | 19 |
| 4 | [GPT OSS 20B](https://models.litellm.ai/models/gpt-oss-20b) | OpenAI | 16 providers | $0.0145 / $0.07 | 128K | 16 |
| 5 | [DeepSeek V3](https://models.litellm.ai/models/deepseek-v3) | DeepSeek | 16 providers | $0.27 / $1.10 | 64K | 16 |
| 6 | [DeepSeek R1](https://models.litellm.ai/models/deepseek-r1) | DeepSeek | 16 providers | $0.55 / $2.19 | 64K | 16 |
| 7 | [DeepSeek V4.1 Flash](https://models.litellm.ai/models/deepseek-v4.1-flash) | DeepSeek | 14 providers | $0.09 / $0.30 | 1M | 14 |
| 8 | [GLM 5.3 Flash](https://models.litellm.ai/models/glm-5.3-flash) | Z.ai | 14 providers | $0.15 / $0.50 | 1M | 14 |
| 9 | [Qwen3 32B](https://models.litellm.ai/models/qwen3-32b) | Alibaba | 11 providers | $0.08 / $0.23 | 32K | 11 |
| 10 | [DeepSeek V3.2](https://models.litellm.ai/models/deepseek-v3.2) | DeepSeek | 10 providers | $0.28 / $0.40 | 160K | 10 |
| 11 | [Qwen3 Next 80B A3B Instruct](https://models.litellm.ai/models/qwen3-next-80b-a3b-instruct) | Alibaba | 10 providers | $0.15 / $1.20 | 256K | 10 |
| 12 | [MiniMax M3](https://models.litellm.ai/models/minimax-m3) | MiniMax | 10 providers | $0.30 / $1.20 | 1M | 10 |
| 13 | [Qwen3 30B A3B](https://models.litellm.ai/models/qwen3-30b-a3b) | Alibaba | 9 providers | $0.09 / $0.20 | 128K | 9 |
| 14 | [DeepSeek R1 Distill Llama 70B](https://models.litellm.ai/models/deepseek-r1-distill-llama-70b) | DeepSeek | 9 providers | $0.20 / $0.60 | 128K | 9 |
| 15 | [Qwen3 Next 80B A3B Thinking](https://models.litellm.ai/models/qwen3-next-80b-a3b-thinking) | Alibaba | 9 providers | $0.15 / $1.20 | 256K | 9 |
| 16 | [GPT-5.6 Luna](https://models.litellm.ai/models/gpt-5.6-luna) | OpenAI | 9 providers | $0.20 / $1.20 | 922K | 9 |
| 17 | [Llama 4 Maverick 17B 128e Instruct](https://models.litellm.ai/models/llama-4-maverick-17b-128e-instruct) | Meta | 9 providers | $0.35 / $1.15 | 1M | 9 |
| 18 | [Qwen3 VL 235B A22B Instruct](https://models.litellm.ai/models/qwen3-vl-235b-a22b-instruct) | Alibaba | 9 providers | $0.40 / $1.60 | 128K | 9 |
| 19 | [Llama3.2 3B Instruct](https://models.litellm.ai/models/llama-3.2-3b-instruct) | Meta | 8 providers | $0.015 / $0.025 | 128K | 8 |
| 20 | [Qwen3.6 35B A3B](https://models.litellm.ai/models/qwen3.6-35b-a3b) | Alibaba | 8 providers | $0.05 / $0.40 | 256K | 8 |