Context Window

Compare

Claude Haiku Latest vs Gpt Oss 120b Ultra

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.

Anthropic

Model

Claude Haiku Latest

Image inputTool calling

Context window

200K

200,000 tokens · ~150K words

Model page
Openai

Model

Gpt Oss 120b Ultra

Tool calling

Context window

131K

131,072 tokens · ~98K 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.

Claude Haiku Latest200K
Gpt Oss 120b Ultra131K

Claude Haiku Latest has about 1.5× the context window of the other in this pair.

Token calculator →Memory savings →

Claude Haiku Latest has 52% more context capacity (200K vs 131K tokens). Gpt Oss 120b Ultra is 80% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Claude Haiku Latest. Its 200K context fits entire documents without chunking (vs 131K).

  • RAG / high-volume retrieval

    Use Gpt Oss 120b Ultra. Input tokens are 80% cheaper — critical when sending large retrieved contexts.

Full specs

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

SpecClaude Haiku LatestGpt Oss 120b Ultra
Context window200,000 tokens (200K)131,072 tokens (131K)
Max output tokens64,000 tokens (64K)N/A
Speed tierFastBalanced
VisionYesNo
Function callingYesYes
Extended thinkingYesYes
Prompt cachingYesNo
Batch APIYesNo
Release dateApr 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.

ProviderClaude Haiku Latest inClaude Haiku Latest outGpt Oss 120b Ultra inGpt Oss 120b Ultra out
Deepinfra——$0.200/M$0.950/M
Openrouter$1.00/M$5.00/M——

Frequently asked questions

Claude Haiku Latest has a larger context window: 200K tokens vs 131K. 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