We track 3516 chat models across 18 API providers. Here are the cheapest per-token options right now.
- Chat models tracked
- 3516
- Providers
- 18
- Cheapest input
- $0.01/1M tokens
| Model | Provider | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Gpt Oss 20b | LiteLLM price JSON | $0.01/1M tokens | $0.07/1M tokens | 131,072 |
| Llama3 2 11b Vision Instruct | LiteLLM price JSON | $0.01/1M tokens | $0.03/1M tokens | 131,072 |
| Llama3 2 3b Instruct | LiteLLM price JSON | $0.01/1M tokens | $0.03/1M tokens | 131,072 |
| Qwen Qwen2 5 Coder 7B | LiteLLM price JSON | $0.01/1M tokens | $0.03/1M tokens | 32,768 |
| Qwen Qwen2 5 Coder 3B Instruct | LiteLLM price JSON | $0.01/1M tokens | $0.03/1M tokens | — |
| Qwen Qwen2 5 Coder 7B Instruct | LiteLLM price JSON | $0.01/1M tokens | $0.03/1M tokens | — |
| @Cf Ibm Granite Granite 4 0 H Micro | LiteLLM price JSON | $0.02/1M tokens | $0.11/1M tokens | 131,000 |
| Google Gemma 4 E4B It | LiteLLM price JSON | $0.02/1M tokens | $0.10/1M tokens | 131,072 |
| Meta Llama Llama 3 2 3B Instruct | LiteLLM price JSON | $0.02/1M tokens | $0.02/1M tokens | 131,072 |
| Meta Llama Meta Llama 3 1 8B Instruct Turbo | LiteLLM price JSON | $0.02/1M tokens | $0.04/1M tokens | 131,072 |
Per-token prices update as listings refresh; see the LLM catalog for filters by capability and context.