LlamaGate model pricing
As of October 10, 2026, 16 LlamaGate models are available through LiteLLM. The most recently added are CodeLlama 7B, DeepSeek Coder 6.7B, DeepSeek R1 7B Qwen. Prices below are LlamaGate's list prices.
LlamaGate models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| CodeLlama 7B | – | $0.06 / $0.12 per 1M tokens | 16K | 1 | Jan 2026 |
| DeepSeek Coder 6.7B | DeepSeek | $0.06 / $0.12 per 1M tokens | 16K | 1 | Jan 2026 |
| DeepSeek R1 7B Qwen | DeepSeek | $0.08 / $0.15 per 1M tokens | 128K | 1 | Jan 2026 |
| DeepSeek R1 8B | DeepSeek | $0.10 / $0.20 per 1M tokens | 64K | 1 | Jan 2026 |
| Dolphin3 8B | – | $0.08 / $0.15 per 1M tokens | 128K | 1 | Jan 2026 |
| Gemma3 4B | $0.03 / $0.08 per 1M tokens | 128K | 1 | Jan 2026 | |
| Llava 7B | – | $0.10 / $0.20 per 1M tokens | 4K | 1 | Jan 2026 |
| Mistral 7B V0.3 | Mistral AI | $0.10 / $0.15 per 1M tokens | 32K | 1 | Jan 2026 |
| Nomic Embed Text | – | $0.02 per 1M tokens | 8K | 1 | Jan 2026 |
| Openthinker 7B | – | $0.08 / $0.15 per 1M tokens | 32K | 1 | Jan 2026 |
| Qwen3 VL 8B | Alibaba | $0.15 / $0.55 per 1M tokens | 32K | 1 | Jan 2026 |
| Qwen3 Embedding 8B | Alibaba | $0.02 per 1M tokens | 40K | 5 | Dec 2025 |
| Qwen2.5 Coder 7B | Alibaba | $0.06 / $0.12 per 1M tokens | 32K | 3 | Aug 2025 |
| Qwen3 8B | Alibaba | $0.04 / $0.14 per 1M tokens | 32K | 3 | Jul 2025 |
| Llama 3.2 3B | Meta | $0.04 / $0.08 per 1M tokens | 128K | 3 | Mar 2025 |
| Llama 3.1 8B | Meta | $0.03 / $0.05 per 1M tokens | 128K | 5 | Sep 2024 |