Compare AI models

Specifications
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.
1M1M
API pricingUSD per 1M tokens · lower wins · base tier
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$0.10—
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$0.50—
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
$0.01—
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page.
$0.10Amazon Bedrock—
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input.
$0.50Amazon Bedrock—
$45.00Anthropic list price—
Benchmarks
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better.
39.2%48.5%
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better.
45.9%51.7%
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit)
15781686
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better.
46.4%54.2%
Overview
CompanyAnthropicQwen
Release dateOct 7 2026Nov 11 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Qwen4-Max leads Claude Haiku 5.5 on 4 of the 4 benchmarks they both report (Terminal-Bench 4.0, Humanity's Last Exam, AA-Briefcase v1.1, Chartography). Only Claude Haiku 5.5 has a verified first-party price for an available API: $0.10 per million input tokens and $0.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen4-Max. Claude Haiku 5.5 shipped 35 days before Qwen4-Max, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Haiku 5.5) vs 1M (Qwen4-Max).

On Terminal-Bench 4.0, Qwen4-Max leads at 48.5% vs Claude Haiku 5.5 at 39.2%. On Humanity's Last Exam · no tools, Qwen4-Max leads at 51.7% vs Claude Haiku 5.5 at 45.9%. On AA-Briefcase v1.1, Qwen4-Max leads at 1686 vs Claude Haiku 5.5 at 1578. On Chartography · no tools, Qwen4-Max leads at 54.2% vs Claude Haiku 5.5 at 46.4%.