Context Window

Compare

Llama 4 Scout 17b 128e Instruct Maas vs Qwen3 235b A22b Thinking 2507 Fp8

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 Scout 17b 128e Instruct Maas

Tool calling

Context window

10M

10,000,000 tokens · ~7.5M words

Model page
Alibaba

Model

Qwen3 235b A22b Thinking 2507 Fp8

Context window

262K

262,141 tokens · ~197K 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 Scout 17b 128e Instruct Maas10M
Qwen3 235b A22b Thinking 2507 Fp8262K

Llama 4 Scout 17b 128e Instruct Maas has about 38.1× the context window of the other in this pair.

Token calculator →Memory savings →

Llama 4 Scout 17b 128e Instruct Maas has 3714% more context capacity (10000K vs 262K tokens). Llama 4 Scout 17b 128e Instruct Maas is 28% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Llama 4 Scout 17b 128e Instruct Maas. Its 10000K context fits entire documents without chunking (vs 262K).

  • RAG / high-volume retrieval

    Use Llama 4 Scout 17b 128e Instruct Maas. Input tokens are 28% cheaper — critical when sending large retrieved contexts.

Full specs

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

SpecLlama 4 Scout 17b 128e Instruct MaasQwen3 235b A22b Thinking 2507 Fp8
Context window10,000,000 tokens (10000K)262,141 tokens (262K)
Max output tokens10,000,000 tokens (10000K)N/A
Speed tierFastDeep
VisionNoNo
Function callingYesNo
Extended thinkingNoNo
Prompt cachingNoNo
Batch APINoNo
Release dateN/AN/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.

ProviderLlama 4 Scout 17b 128e Instruct Maas inLlama 4 Scout 17b 128e Instruct Maas outQwen3 235b A22b Thinking 2507 Fp8 inQwen3 235b A22b Thinking 2507 Fp8 out
Gmi——$0.350/M$4.20/M
Google Vertex$0.250/M$0.700/M——

Frequently asked questions

Llama 4 Scout 17b 128e Instruct Maas has a larger context window: 10000K tokens vs 262K. 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