Context Window

Compare

Chat Bison 001 vs Moonshot V1 8k Vision Preview

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.

Google

Model

Chat Bison 001

Context window

8K

8,192 tokens · ~6K words

Model page
Moonshot

Model

Moonshot V1 8k Vision Preview

Image inputTool calling

Context window

8K

8,192 tokens · ~6K 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.

Chat Bison 0018K
Moonshot V1 8k Vision Preview8K

Same context window size for both models.

Token calculator →Memory savings →

Chat Bison 001 and Moonshot V1 8k Vision Preview have identical context windows (8K tokens). Chat Bison 001 is 37% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • RAG / high-volume retrieval

    Use Chat Bison 001. Input tokens are 37% cheaper — critical when sending large retrieved contexts.

  • Long output (reports, code files)

    Use Moonshot V1 8k Vision Preview. Its 8K 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.

SpecChat Bison 001Moonshot V1 8k Vision Preview
Context window8,192 tokens (8K)8,192 tokens (8K)
Max output tokens4,096 tokens (4K)8,192 tokens (8K)
Speed tierBalancedBalanced
VisionNoYes
Function callingNoYes
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.

ProviderChat Bison 001 inChat Bison 001 outMoonshot V1 8k Vision Preview inMoonshot V1 8k Vision Preview out
Google$0.125/M$0.125/M——
Moonshot——$0.200/M$2.00/M

Frequently asked questions

Moonshot V1 8k Vision Preview has a larger context window: 8K tokens vs 8K. 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