Context Window

Compare

Llama 4 Maverick 17b 128e Instruct Fp8 vs Nemotron 3 Ultra (free)

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.

Meta

Model

Llama 4 Maverick 17b 128e Instruct Fp8

Image inputTool calling

Context window

1M

1,000,000 tokens · ~750K words

Model page
Nvidia

Model

Nemotron 3 Ultra (free)

Tool calling

Context window

1M

1,000,000 tokens · ~750K 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.

Llama 4 Maverick 17b 128e Instruct Fp81M
Nemotron 3 Ultra (free)1M

Same context window size for both models.

Token calculator →Memory savings →

Llama 4 Maverick 17b 128e Instruct Fp8 and Nemotron 3 Ultra (free) have identical context windows (1000K tokens).

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long output (reports, code files)

    Use Nemotron 3 Ultra (free). Its 65K max output lets you generate complete artifacts in one request.

Full specs

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

SpecLlama 4 Maverick 17b 128e Instruct Fp8Nemotron 3 Ultra (free)
Context window1,000,000 tokens (1000K)1,000,000 tokens (1000K)
Max output tokens16,384 tokens (16K)65,536 tokens (65K)
Speed tierFastBalanced
VisionYesNo
Function callingYesYes
Extended thinkingNoYes
Prompt cachingNoNo
Batch APINoNo
Release dateN/AJun 2026

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.

ProviderLlama 4 Maverick 17b 128e Instruct Fp8 inLlama 4 Maverick 17b 128e Instruct Fp8 outNemotron 3 Ultra (free) inNemotron 3 Ultra (free) out
Azure$1.41/M$0.350/M——
Deepinfra$0.150/M$0.600/M——
Lambda$0.050/M$0.100/M——
Meta————
Novita$0.270/M$0.850/M——
Together Ai$0.270/M$0.850/M——

Frequently asked questions

Nemotron 3 Ultra (free) has a larger context window: 1000K tokens vs 1000K. 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