Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.
Use of this model is subject to Cohere's Acceptable Use Policy.
Anthropic's model for low-latency, high throughput text generation. Supports hundreds of pages of text.
This is a faster endpoint, made available in collaboration with Anthropic, that is self-moderated: response moderation happens on the provider's side instead of OpenRouter's. For requests that pass moderation, it's identical to the Standard variant.
Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
The model was trained on synthetic data.
These are free, rate-limited endpoints for Reflection 70B. Outputs may be cached. Read about rate limits here.