Speed
90.5 output tokens/secDeep Cogito · Flagships Analysis
Cogito v2.1
Intelligence, Performance & Price Analysis
Canonical slug: cogito-v2-1-reasoning · Canonical model registry at build time
Latency
0.85s TTFTInput Price
$1.25 / 1M tokensOutput Price
$1.25 / 1M tokensExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
General purpose assistant
Cogito v2.1 (Reasoning) generates output at 90.5 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 64.8 t/s). Cogito v2.1 (Reasoning) costs $1.25 per 1M input tokens (at the higher end, median: $0.59) and $1.25 per 1M output tokens (better than average, median: $2.20), based on the median across providers serving the model.
Route complex or high-value tasks here when the extra capability justifies the cost.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Latency-sensitive applications | optimal | TTFT 0.85s — among the lowest latencies, suitable for interactive latency-critical use cases. |
| Cost-sensitive pipelines | optimal | Output pricing at $1.25 is reasonable for moderate volume. |
Cost Pressure Analysis
High
Pricing is premium — input $1.25, output $1.25. This model is expensive for high-volume or output-heavy workloads.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | Yes | faq |
| Input modalities | Cogito v2.1 (Reasoning) supports text input. | faq |
| Output modalities | Cogito v2.1 (Reasoning) supports text output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | Yes, Cogito v2.1 (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Cogito v2.1 (Reasoning) has 671 billion parameters (37 billion active). | faq |
| Active parameters | Cogito v2.1 (Reasoning) is a Mixture of Experts (MoE) model with 671 billion total parameters, but only 37 billion active parameters are used during inference. | faq |
| License | Cogito v2.1 (Reasoning) is released under the MIT license. This license allows commercial use. | faq |
| API availability | Yes, Cogito v2.1 (Reasoning) is available via API through 1 provider. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Cogito v2.1.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
Cogito v2.1 (Reasoning) was released on November 18, 2025.
Cogito v2.1 (Reasoning) was created by Deep Cogito.
Cogito v2.1 (Reasoning) generates output at 90.5 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 64.8 t/s).
Cogito v2.1 (Reasoning) has a time to first token (TTFT) of 0.85s (based on the median across providers serving the model), which is very competitive compared to other open weight models of similar size (median: 2.03s).
Cogito v2.1 (Reasoning) costs $1.25 per 1M input tokens (at the higher end, median: $0.59) and $1.25 per 1M output tokens (better than average, median: $2.20), based on the median across providers serving the model.
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 (7:2:1 cache hit/input/output ratio), this is $1.25 per 1M tokens. Pricing may vary by provider.
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.
Cogito v2.1 (Reasoning) supports text input.
Cogito v2.1 (Reasoning) supports text output.
No, Cogito v2.1 (Reasoning) does not support image input. It can only process text.
No, Cogito v2.1 (Reasoning) is not multimodal. It only supports text input.
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.
Yes, Cogito v2.1 (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Cogito v2.1 (Reasoning) has 671 billion parameters (37 billion active).
Cogito v2.1 (Reasoning) is a Mixture of Experts (MoE) model with 671 billion total parameters, but only 37 billion active parameters are used during inference.
Cogito v2.1 (Reasoning) is released under the MIT license. This license allows commercial use.
Yes, Cogito v2.1 (Reasoning) is available via API through 1 provider.
Cogito v2.1 (Reasoning) is available through 1 API provider.