Zerogpu LLM API pricing
Every model Zerogpu serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models Zerogpu lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
13
on this provider
Cheapest input
$0.02
per 1M tokens
Cheapest output
$0.05
per 1M tokens
Max context
1.1M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Lfm2 5.1 2B Instruct | Other | 33K | $0.02 | $0.05 | zerogpu/LFM2.5-1.2B-Instruct |
| Lfm2 5.1 2B Thinking | Other | 33K | $0.02 | $0.05 | zerogpu/LFM2.5-1.2B-Thinking |
| Llama 3.2 3B Instruct Fast | Meta | 131K | $0.05 | $0.30 | zerogpu/llama-3.2-3b-instruct-fast |
| GLM 5.3 Flash | Zhipu | 1M | $0.10 | $0.35 | zerogpu/glm-5.3-flash |
| GPT-6 Luna | OpenAI | 922K | $0.10 | $0.50 | zerogpu/gpt-6-luna |
| Qwen3 30B A3b FP8 | Alibaba | 41K | $0.10 | $0.45 | zerogpu/qwen3-30b-a3b-fp8 |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | zerogpu/gpt-oss-120b |
| Llama 3.1 8B Instruct Fast | Meta | 131K | $0.15 | $0.28 | zerogpu/llama-3.1-8b-instruct-fast |
| GPT-5.4 Nano | OpenAI | 400K | $0.20 | $1.25 | zerogpu/gpt-5.4-nano |
| GPT-5.6 Luna | OpenAI | 1.1M | $0.20 | $1.20 | zerogpu/gpt-5.6-luna |
| Qwen3.6 35B A3B | Alibaba | 262K | $0.20 | $1.50 | zerogpu/qwen3.6-35b-a3b |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.30 | $1.20 | zerogpu/deepseek-v4.1-flash |
| GPT-4.1 Mini | OpenAI | 1M | $0.40 | $1.60 | zerogpu/gpt-4.1-mini |
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 29, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI