Alpindale: Goliath 120B

Public pricingIntelligence 79/100Small memory

Goliath 120B — это текстовой‑модель для общение, анализ и продакшн-задачи. Она сочетает стабильную универсальную работу, контекст 6K tokens и профиль премиальный, обеспечивая надёжную работу в задачах general chat, analysis, and production workloads. Это практичный выбор, когда важен качество, скорость и стоимость, особенно для команд, которым нужны стабильные ответы,

Input

$3.75/1M

Output

$7.50/1M

Cached

$0.38/1M

Batch

$1.88/1M

Calculate your Goliath 120B bill.

Set your workload — see cost at your exact volume.

What would Goliath 120B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Goliath 120B at a glance.

Memory

6,144

tokens

Max reply

1,024

tokens

Memory tier

Small

a few emails or a short document

Tokenizer

llama2

Released

Nov 2023

Training cutoff

Jul 2023

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 Goliath 120B

  • Goliath 120B fits general-purpose text tasks within its memory tier.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.
  • You need tool-use / function calling for agent workflows.
  • Your inputs routinely exceed short documents.

Alternatives

Similar models to compare.

FAQ

Goliath 120B — 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, Goliath 120B costs roughly $581 per month. Input is $3.75 /1M tokens and output is $7.50 /1M tokens.
Goliath 120B has a 6,144-token context window (small memory — a few emails or a short document). That means you can fit about 1,152 words of input and history in a single call.
Goliath 120B was released in November 2023, with training data cut off around July 2023.
Models in a similar class include Aion-1.0, Claude 3.7 Sonnet, Claude 3.7 Sonnet (thinking). The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Goliath 120B 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.

Open the comparison wizard