Provider
zerogpu
13 Models · 13 Prices · Cheapest on 5 · Uptime — · updated 2026-11-03 08:16 UTC
Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).
Models served
| Model | $ in /1M | $ out /1M | Cheapest | Router / Source | Evidence |
|---|---|---|---|---|---|
| LFM2.5-1.2B-Instruct | $0.020 | $0.050 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| LFM2.5-1.2B-Thinking | $0.020 | $0.050 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| llama-3.2-3b-instruct-fast | $0.050 | $0.300 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| glm-5.3-flash | $0.100 | $0.350 | — | Pricebook (LiteLLM) ↗ | Official list |
| llama-3.1-8b-instruct-fast | $0.150 | $0.280 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| qwen3-30b-a3b-fp8 | $0.100 | $0.450 | — | Pricebook (LiteLLM) ↗ | Official list |
| gpt-6-luna | $0.100 | $0.500 | — | Pricebook (LiteLLM) ↗ | Official list |
| gpt-oss-120b | $0.150 | $0.600 | — | Pricebook (LiteLLM) ↗ | Official list |
| gpt-5.6-luna | $0.200 | $1.20 | — | Pricebook (LiteLLM) ↗ | Official list |
| gpt-5.4-nano | $0.200 | $1.25 | — | Pricebook (LiteLLM) ↗ | Official list |
| deepseek-v4.1-flash | $0.300 | $1.20 | — | Pricebook (LiteLLM) ↗ | Official list |
| qwen3.6-35b-a3b | $0.200 | $1.50 | — | Pricebook (LiteLLM) ↗ | Official list |
| gpt-4.1-mini | $0.400 | $1.60 | ✓ | Pricebook (LiteLLM) ↗ | Official list |