Cogito v2 preview 671B MoE
Pricing & Specs

Deep Cogito · $1.25 input / $1.25 output per 1M tokens · 163.84K context window

No longer offered on OpenMark

$1.25
per 1M input tokens
$1.25
per 1M output tokens
163.84K
context window (tokens)

Cogito v2 preview 671B MoE is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Cogito v2 preview 671B MoE API Pricing

TokensPrice
Input$1.25 / 1M tokens
Output$1.25 / 1M tokens

Batch API pricing is available via Together at 50%; cache pricing is not published.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0019
1K 1,000 runs of that task: $1.88
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Cogito v2 preview 671B MoE Specs

SpecValue
Context window163.84K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~383ms median response
Reasoning modelNo
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo
Batch APIYes

Capabilities

chat reasoning

FAQ

How much does Cogito v2 preview 671B MoE cost?

Cogito v2 preview 671B MoE costs $1.25 per 1M input tokens and $1.25 per 1M output tokens.

What is Cogito v2 preview 671B MoE's context window?

Cogito v2 preview 671B MoE has a 163.84K-token context window.

Can I test Cogito v2 preview 671B MoE on my own task?

Cogito v2 preview 671B MoE is no longer offered on OpenMark, but you can benchmark its current alternatives from Deep Cogito and other providers on your own task — free tier available.

Still using Cogito v2 preview 671B MoE?

It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives — Free →