Router mode
In router mode, OpenCompress routes your request through OpenRouter, giving you access to hundreds of models. Here are the most popular:
OpenAI
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|
gpt-4o | $2.50 | $10.00 |
gpt-4o-mini | $0.15 | $0.60 |
gpt-4-turbo | $10.00 | $30.00 |
gpt-4.1 | $2.00 | $8.00 |
gpt-4.1-mini | $0.40 | $1.60 |
gpt-4.1-nano | $0.10 | $0.40 |
Anthropic
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|
claude-opus-4-6 | $15.00 | $75.00 |
claude-sonnet-4-6 | $3.00 | $15.00 |
claude-haiku-4-5-20251001 | $0.80 | $4.00 |
Google
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|
gemini-2.5-pro | $1.25 | $10.00 |
gemini-2.5-flash | $0.15 | $0.60 |
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|
meta-llama/llama-4-maverick | $0.20 | $0.60 |
meta-llama/llama-4-scout | $0.15 | $0.40 |
DeepSeek
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|
deepseek/deepseek-chat-v3-0324 | $0.50 | $1.50 |
deepseek/deepseek-r1 | $0.50 | $2.00 |
Prices shown are the base LLM cost before compression savings. With OpenCompress, your effective cost is lower because fewer tokens are sent.
BYOK mode
In BYOK mode, you can use any model from any provider. Just provide your own API key and base URL. See BYOK Mode for details.
Model not listed?
If a model is available on OpenRouter, it works with OpenCompress. Use the exact model identifier from OpenRouter’s model list.
