Deep Cogito: Cogito v2.1 671B

Public pricingIntelligence 79/100Medium memory深度思考工具调用

Deep Cogito: Cogito v2.1 671B 是一款文本模型,适合通用对话、分析与生产场景。它结合了稳定的通用表现、128K tokens上下文和均衡成本定位,可在general chat, analysis, and production workloads中提供可靠表现。它适合重视质量、速度与成本的团队,能带来稳定输出、灵活部署与扩展空间。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。

Input

$1.25/1M

Output

$1.25/1M

Cached

$0.06/1M

Batch

$0.30/1M

Calculate your Cogito v2.1 671B bill.

Set your workload — see cost at your exact volume.

What would Cogito v2.1 671B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Cogito v2.1 671B at a glance.

Memory

128,000

tokens

Max reply

32,768

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

Released

Nov 2025

Training cutoff

Jun 2025

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Cogito v2.1 671B

  • Multi-step reasoning, research agents, or hard math.
  • Agentic workflows that call tools or APIs.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

FAQ

Cogito v2.1 671B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Cogito v2.1 671B costs roughly $144 per month. Input is $1.25 /1M tokens and output is $1.25 /1M tokens.
Cogito v2.1 671B has a 128,000-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,000 words of input and history in a single call.
Beyond text generation, Cogito v2.1 671B supports deep step-by-step reasoning, calling functions / tools, strict JSON output. It streams replies by default.
Cogito v2.1 671B was released in November 2025, with training data cut off around June 2025.
Models in a similar class include Gemini 2.5 Pro, Gemini 2.5 Pro Preview 05-06, Gemini 2.5 Pro Preview 06-05. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Cogito v2.1 671B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.