---
id: "deepcogito/cogito-v2.1-671b"
also: ["deepcogito/cogito-v2.1-671b-20251118"]
cheapest_list_usd_per_m: "1.25 in, 1.25 out, at together on openrouter"
cheapest_effective_usd_per_m: "1.2498 in, 1.2436 out, at together on openrouter"
context: 128000
input: ["text"]
output: ["text"]
released: "2025-11-13"
params: ["frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# Deep Cogito: Cogito v2.1 671B

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...