Cogito v2.1 (Reasoning)
Intelligence
—
Coding
24.8
Math
72.7
#89/265
Speed
94 tok/s
TTFT: 332.00s
Pricing
$1.25 / $1.25
per 1M tokens (in/out)
Cogito v2.1 (Reasoning) by Deep Cogito is designed for advanced reasoning tasks. It processes at 93.697 tokens per second and is priced at $1.25 per million tokens, targeting professional users in analytical fields.
When to Use Cogito v2.1 (Reasoning)
✓ Best For
- Complex problem solving
- Data analysis and interpretation
- Mathematical reasoning tasks
✗ Not Ideal For
- Basic coding tasks
- Real-time applications requiring low latency
How Cogito v2.1 (Reasoning) Compares
Benchmark Profile
All Benchmark Scores (11)
| Benchmark | Score | |
|---|---|---|
| Coding Index | 24.8 | |
| Math Index | 72.7 | |
| MMLU-Pro | 849% | |
| GPQA | 768% | |
| LiveCodeBench | 688% | |
| HLE | 11% | |
| SciCode | 41% | |
| IFBench | 46.3% | |
| LCR | 21.7% | |
| TerminalBench Hard | 16.7% | |
| AIME 2025 | 72.7% |
Data: Artificial Analysis · Updated: March 27, 2026
Frequently Asked Questions (15)
When was Cogito v2.1 (Reasoning) released?
Cogito v2.1 (Reasoning) was released on November 18, 2025.
Who created Cogito v2.1 (Reasoning)?
Cogito v2.1 (Reasoning) was created by Deep Cogito.
How fast is Cogito v2.1 (Reasoning)?
Cogito v2.1 (Reasoning) generates output at 89.0 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 54.8 t/s).
What is the latency of Cogito v2.1 (Reasoning)?
Cogito v2.1 (Reasoning) has a time to first token (TTFT) of 0.71s (based on the median across providers serving the model), which is very competitive compared to other open weight models of similar size (median: 2.17s).
How much does Cogito v2.1 (Reasoning) cost?
Cogito v2.1 (Reasoning) costs $1.25 per 1M input tokens (at the higher end, median: $0.60) and $1.25 per 1M output tokens (better than average, median: $2.20), based on the median across providers serving the model.
What is Cogito v2.1 (Reasoning) API pricing?
Cogito v2.1 (Reasoning) costs $1.25 per 1M input tokens and $1.25 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $1.25 per 1M tokens. Pricing may vary by provider.
How verbose is Cogito v2.1 (Reasoning)?
When evaluated on the Intelligence Index, Cogito v2.1 (Reasoning) generated 19M output tokens, which is better than average compared to other open weight models of similar size (median: 17M).
Is Cogito v2.1 (Reasoning) a reasoning model?
Yes, Cogito v2.1 (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Cogito v2.1 (Reasoning) support?
Cogito v2.1 (Reasoning) supports text input.
What output modalities does Cogito v2.1 (Reasoning) support?
Cogito v2.1 (Reasoning) supports text output.
Can Cogito v2.1 (Reasoning) process images?
No, Cogito v2.1 (Reasoning) does not support image input. It can only process text.
Is Cogito v2.1 (Reasoning) multimodal?
No, Cogito v2.1 (Reasoning) is not multimodal. It only supports text input.
What is the context window of Cogito v2.1 (Reasoning)?
Cogito v2.1 (Reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Cogito v2.1 (Reasoning) open source?
Yes, Cogito v2.1 (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Cogito v2.1 (Reasoning) have?
Cogito v2.1 (Reasoning) has 671 billion parameters (37 billion active).
