AI Observatory / Model Radar
Deepcogito / deepcogito/cogito-v2.1-671b
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...
128,000
Context
N/A
Max output
$1.25 / 1M
Prompt price
2025-11-13
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Deepcogito | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $1.25 / 1M |
| Completion price | $1.25 / 1M | Request price | N/A |
| Context length | 128,000 | Max completion tokens | N/A |
| Supported parameters | 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 | ||
Best for
deepcogito/cogito-v2.1-671b
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...
High-volume usage
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.