Context Window

Compare

Grok 4.20 Multi-Agent vs Meta Llama3 2 90b Instruct

This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.

Xai

Model

Grok 4.20 Multi-Agent

Image input

Context window

2M

2,000,000 tokens · ~1.5M words

Model page
Meta

Model

Meta Llama3 2 90b Instruct

Image inputTool calling

Context window

128K

128,000 tokens · ~96K words

Model page

Context window · side by side

Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.

Grok 4.20 Multi-Agent2M
Meta Llama3 2 90b Instruct128K

Grok 4.20 Multi-Agent has about 15.6× the context window of the other in this pair.

Token calculator →Memory savings →

Grok 4.20 Multi-Agent has 1462% more context capacity (2000K vs 128K tokens).

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Grok 4.20 Multi-Agent. Its 2000K context fits entire documents without chunking (vs 128K).

Full specs

Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.

SpecGrok 4.20 Multi-AgentMeta Llama3 2 90b Instruct
Context window2,000,000 tokens (2000K)128,000 tokens (128K)
Max output tokensN/A4,096 tokens (4K)
Speed tierBalancedBalanced
VisionYesYes
Function callingNoYes
Extended thinkingYesNo
Prompt cachingYesNo
Batch APINoNo
Release dateMar 2026N/A

Pricing matrix

Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.

ProviderGrok 4.20 Multi-Agent inGrok 4.20 Multi-Agent outMeta Llama3 2 90b Instruct inMeta Llama3 2 90b Instruct out
Aws Bedrock——$2.00/M$2.00/M

Frequently asked questions

Grok 4.20 Multi-Agent has a larger context window: 2000K tokens vs 128K. For long documents, large codebases, or extended agent sessions, the larger context window reduces the need to chunk inputs or summarize history.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Calculate your savingsLearn about Mem0

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model