Active production language models ranked strictly by standard API price per 1 million input tokens. Deprecated endpoints and unlaunched catalog listings are segregated into a separate historical section below.
| Rank | Model | Provider | Input / 1M | Cached / 1M | Output / 1M | Context |
|---|---|---|---|---|---|---|
| #1 | Gemini 2.5 Flash-Lite | $0.10 | $0.01 | $0.40 | 1.05M | |
| #2 | Mistral Small 4 | Mistral AI | $0.15 | $0.015 | $0.60 | 256k |
| #3 | GPT-5.6 Luna | OpenAI | $0.20 | $0.02 | $1.20 | 1.05M |
| #4 | Llama 4 Vivas | Meta / Together | $0.25 | $0.06 | $0.85 | 1M |
| #5 | DeepSeek-V4.1-Reasoner | DeepSeek | $0.28 | $0.028 | $0.42 | 256k |
| Model | Status | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| DeepSeek-V3 (Legacy API Alias) | Legacy Reference | $0.14 | $0.28 | 128k |
| Command R (08-2024) | Legacy Reference | $0.15 | $0.60 | 128k |
| Llama 4 Scout (17B Active / 109B MoE) — Together AI | Legacy Reference | $0.18 | $0.59 | 328k |
| Grok 2 mini | Legacy Reference | $0.20 | $1.00 | 128k |
| Llama 4 Maverick (400B) — Together AI | Legacy Reference | $0.27 | $0.85 | 1M |