LLM token prices: zerogpu
LLM API prices per 1M tokens: input, output and cached input, from each provider's listing or the LiteLLM cross-check.
Sources for this list
- Last verified 2026-10-28T23:57:27+00:00 · https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json (community cross-check,
litellm)
No first-party source is read for this model yet; this value is a community cross-check and can lag the provider.
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| LFM2.5-1.2B-Instruct | LFM2.5-1.2B-Instruct | USD 0.02 | USD 0.05 | – | 32,768 | 2026-10-28 23:57 UTC | source cross-check |
| LFM2.5-1.2B-Thinking | LFM2.5-1.2B-Thinking | USD 0.02 | USD 0.05 | – | 32,768 | 2026-10-28 23:57 UTC | source cross-check |
| deepseek-v4.1-flash | deepseek-v4.1-flash | USD 0.30 | USD 1.20 | USD 0.003 | 1,048,576 | 2026-10-28 23:57 UTC | source cross-check |
| glm-5.3-flash | glm-5.3-flash | USD 0.10 | USD 0.35 | USD 0.015 | 1,048,576 | 2026-10-28 23:57 UTC | source cross-check |
| gpt-oss-120b | gpt-oss-120b | USD 0.15 | USD 0.60 | USD 0.03 | 128,000 | 2026-10-28 23:57 UTC | source cross-check |
| llama-3.1-8b-instruct-fast | llama-3.1-8b-instruct-fast | USD 0.15 | USD 0.28 | USD 0.025 | 131,072 | 2026-10-28 23:57 UTC | source cross-check |
| llama-3.2-3b-instruct-fast | llama-3.2-3b-instruct-fast | USD 0.05 | USD 0.30 | USD 0.025 | 131,072 | 2026-10-28 23:57 UTC | source cross-check |
| qwen3-30b-a3b-fp8 | qwen3-30b-a3b-fp8 | USD 0.10 | USD 0.45 | USD 0.05 | 32,768 | 2026-10-28 23:57 UTC | source cross-check |
| qwen3.6-35b-a3b | qwen3.6-35b-a3b | USD 0.20 | USD 1.50 | USD 0.20 | 262,144 | 2026-10-28 23:57 UTC | source cross-check |
| zerogpu/gpt-4.1-mini | USD 0.40 | USD 1.60 | USD 0.10 | 1,047,576 | 2026-10-28 23:57 UTC | source cross-check | |
| zerogpu/gpt-5.4-nano | USD 0.20 | USD 1.25 | USD 0.02 | 272,000 | 2026-10-28 23:57 UTC | source cross-check | |
| zerogpu/gpt-5.6-luna | USD 0.20 | USD 1.20 | USD 0.20 | 272,000 | 2026-10-28 23:57 UTC | source cross-check | |
| zerogpu/gpt-6-luna | USD 0.10 | USD 0.50 | USD 0.01 | 272,000 | 2026-10-28 23:57 UTC | source cross-check |