Benchable
Text input
Text output
Author's Description
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 to reach state-of-the-art performance on multiple categories (instruction following, coding, longer queries and creative writing). This advanced system demonstrates significant progress toward scalable superintelligence through policy improvement.
Key Specifications
Context
128K
Parameters
671B
Released
Nov 13, 2025
Supported Parameters
This model supports the following parameters:
Structured Outputs
Max Tokens
Response Format
Stop
Include Reasoning
Top P
Min P
Presence Penalty
Reasoning
Logit Bias
Temperature
Frequency Penalty
Features
This model supports the following features:
Reasoning
Structured Outputs
Response Format
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $1.25 |
| Completion | $1.25 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Together
|
Together | deepcogito/cogito-v2.1-671b-20251118 | 128K | $1.25 / 1M tokens | $1.25 / 1M tokens |
No benchmark execution results are available for this model yet.
Other Models by deepcogito
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Deep Cogito: Cogito V2 Preview Llama 405B Unavailable | Oct 17, 2025 | 405B | 32K |
Text input
Text output
|
— | — | $$$$$ |
| Deep Cogito: Cogito V2 Preview Llama 70B | Sep 02, 2025 | 70B | 32K |
Text input
Text output
|
— | — | $$$$ |
| Cogito V2 Preview Llama 109B | Sep 02, 2025 | 109B | 32K |
Image input
Text input
Text output
|
★★★★★ | ★ | $$ |
| Deep Cogito: Cogito V2 Preview Deepseek 671B | Sep 02, 2025 | 671B | 163K |
Text input
Text output
|
★★★ | ★ | $$$$ |