ZeroGPU
9 modelsProvider docs
As of Nov 22, 2026, ZeroGPU lists 9 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, GPT-5.6 Luna, Qwen3.6 35B-A3B and GPT-5.4 nano across the deepseek-flash, glm-flash, gpt-luna, qwen, gpt-nano and gpt-oss families. The cheapest rate in the table is Llama-3.1-8B-Instruct at $0.28 per 1M output tokens, the priciest GPT-4.1 mini at $1.6. On a 3:1 input:output blend the metered rates span $0.1625–$0.7 per 1M tokens, and every price is ZeroGPU's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
9 of 9 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.3 | $1.2 | $0.003 | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | $0.1 | $0.35 | — | 1.0M | Aug 26, 2026 |
| GPT-5.6 Luna | $0.2 | $1.2 | $0.2 | 272k | Jul 9, 2026 |
| Qwen3.6 35B-A3B | $0.2 | $1.5 | $0.2 | 262k | Apr 17, 2026 |
| GPT-5.4 nano | $0.2 | $1.25 | $0.02 | 400k | Mar 17, 2026 |
| GPT OSS 120B | $0.15 | $0.6 | — | 131k | Aug 5, 2025 |
| Qwen3 30B A3B | $0.1 | $0.45 | — | 33k | Apr 28, 2025 |
| GPT-4.1 mini | $0.4 | $1.6 | $0.1 | 1.0M | Apr 14, 2025 |
| Llama-3.1-8B-Instruct | $0.15 | $0.28 | — | 131k | Jul 23, 2024 |