ZeroGPU model pricing
As of October 31, 2026, 13 ZeroGPU models are available through LiteLLM. The most recently added are Lfm2.5 1.2B Instruct, Lfm2.5 1.2B Thinking, Llama 3.1 8B Instruct Fast. Prices below are ZeroGPU's list prices.
Cheapest chat models on ZeroGPU
Sorted by ZeroGPU's own prices, blended at 3 input tokens per output token. Active chat models only.
| # | Model | Blended per 1M | Input / output per 1M | Context |
|---|---|---|---|---|
| 1 | Lfm2.5 1.2B Instruct | $0.0275 | $0.02 / $0.05 | 32K |
| 2 | Lfm2.5 1.2B Thinking | $0.0275 | $0.02 / $0.05 | 32K |
| 3 | Llama 3.2 3B Instruct Fast | $0.1125 | $0.05 / $0.30 | 128K |
| 4 | GLM 5.3 Flash | $0.1625 | $0.10 / $0.35 | 1M |
| 5 | Llama 3.1 8B Instruct Fast | $0.1825 | $0.15 / $0.28 | 128K |
| 6 | Qwen3 30B A3B | $0.1875 | $0.10 / $0.45 | 32K |
| 7 | GPT-6 Luna | $0.20 | $0.10 / $0.50 | 272K |
| 8 | GPT OSS 120B | $0.2625 | $0.15 / $0.60 | 128K |
| 9 | GPT-5.6 Luna | $0.45 | $0.20 / $1.20 | 272K |
| 10 | DeepSeek V4.1 Flash | $0.525 | $0.30 / $1.20 | 1M |
ZeroGPU models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| Lfm2.5 1.2B Instruct | – | $0.02 / $0.05 per 1M tokens | 32K | 1 | Oct 2026 |
| Lfm2.5 1.2B Thinking | – | $0.02 / $0.05 per 1M tokens | 32K | 1 | Oct 2026 |
| Llama 3.1 8B Instruct Fast | Meta | $0.15 / $0.28 per 1M tokens | 128K | 1 | Oct 2026 |
| Llama 3.2 3B Instruct Fast | Meta | $0.05 / $0.30 per 1M tokens | 128K | 1 | Oct 2026 |
| GPT-6 Luna | OpenAI | $0.10 / $0.50 per 1M tokens | 272K | 12 | Sep 2026 |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 / $1.20 per 1M tokens | 1M | 22 | Sep 2026 |
| GLM 5.3 Flash | Z.ai | $0.10 / $0.35 per 1M tokens | 1M | 21 | Aug 2026 |
| GPT-5.6 Luna | OpenAI | $0.20 / $1.20 per 1M tokens | 272K | 12 | Jul 2026 |
| Qwen3.6 35B A3B | Alibaba | $0.20 / $1.50 per 1M tokens | 256K | 10 | Jun 2026 |
| GPT-5.4 Nano | OpenAI | $0.20 / $1.25 per 1M tokens | 272K | 8 | Mar 2026 |
| GPT OSS 120B | OpenAI | $0.15 / $0.60 per 1M tokens | 128K | 27 | Aug 2025 |
| Qwen3 30B A3B | Alibaba | $0.10 / $0.45 per 1M tokens | 32K | 10 | Jul 2025 |
| GPT-4.1 Mini | OpenAI | $0.40 / $1.60 per 1M tokens | 1M | 5 | Apr 2025 |