Frontier and high-throughput language models ranked strictly by API price per 1 million input tokens.
| Rank | Model | Provider | Input / 1M | Cached / 1M | Output / 1M | Context |
|---|---|---|---|---|---|---|
| #1 | Gemini 2.5 Flash-Lite | $0.100 | $0.025 | $0.400 | 1.05M | |
| #2 | Mistral Small 4 | Mistral AI | $0.150 | $0.030 | $0.600 | 128k |
| #3 | GPT-5.6 Luna | OpenAI | $0.200 | $0.100 | $1.200 | 128k |
| #4 | DeepSeek-V4.1-Flash | DeepSeek | $0.200 | $0.005 | $0.800 | 1.05M |
| #5 | Llama 4 Scout (109B) | Meta / Open | $0.300 | None | $0.600 | 10M |