modelgrep
D

Deep Cogito: Cogito v2.1 671B

deepcogito/cogito-v2.1-671b

ReasoningJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
27
250th fastest
Latency
367ms
first token
Input price
$1.25
221st cheapest
Context
128K

How it compares

Faster than19%
of all ranked models
Cheaper than26%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis
Coding Index
24.8
GPQA Diamond
77%
Humanity's Last Exam
11%
SciCode
41%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Together$1.25$1.25100%

Specifications

Context window128K
Max output
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Cogito v2.1 671B FAQ

How much does Cogito v2.1 671B cost?

Cogito v2.1 671B costs $1.25 per million input tokens and $1.25 per million output tokens via OpenRouter, making it 221st cheapest of 298 paid models.

How fast is Cogito v2.1 671B?

Cogito v2.1 671B generates around 27 tokens per second with 367ms time-to-first-token (p50), the 250th fastest tracked model.

What is Cogito v2.1 671B's context window?

Cogito v2.1 671B supports a 128K-token context window. It accepts text input.