Model profile
Deep Cogito

Cogito v2.1 (Reasoning)

Cogito v2.1 (Reasoning) is a budget-priced text-first model from Deep Cogito with partial runtime data, partial context coverage, and the clearest fit around coding / agent workflows.

Best for: Coding / Agent workflowsN/A latencyN/A contextBudget pricing
Intelligence
N/A

Benchmark blend

Coding
0.688

Dev workflow signal

Context
N/A

N/A

Input Price
$1.25

Budget tier

Decision snapshot
77

Cogito v2.1 (Reasoning) currently reads as a budget text-first option with partially published context and a partially published runtime profile.

Overall profile
Strong all-rounder
Best for
Coding / Agent workflows
Latency tier
N/A
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
N/A
N/A

General reasoning and benchmark headroom.

Unavailable
Speed
N/A
N/A

Latency data is partial.

Unavailable
Context
N/A
N/A

How much prompt and task state can stay in view.

Unavailable
Price
$1.25
86

$1.25 output / 1M

Efficient

Editorial Profile

Cogito v2.1 (Reasoning) in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Strong all-rounderCoding score 69Math score 73

The Cogito v2.1 (Reasoning) AI model by Deep Cogito.

Identity

Deep Cogito text-first profile

Positioning

Coding / Agent workflows with partially published context and partially published runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • Coding indicators point to a strong developer workflow fit.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency data is incomplete, so interactive responsiveness is harder to rank confidently.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

  • Context limits are only partially published, so long-session planning needs extra validation.

Best fit
  • Code generation, refactors, test writing, and tool-assisted debugging.

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

MMLU Pro
84.9%
GPQA
76.8%
HLE
12.0%
Coding

Software implementation, debugging quality, and coding benchmark signal.

LiveCodeBench
0.688
SciCode
41.0%
Math

Formal reasoning, structured problem solving, and competition-style math.

Math Index
72.7
AIME 2025
72.7%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
46.3%
TerminalBench Hard
16.7%
LCR
22.0%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
N/A
Vision
Text-first
Price architecture
Input
per 1M input tokens
$1.25
Output
per 1M output tokens
$1.25
Blended
AA 3:1 mix
$1.25

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.