Warp

Claude Opus 4.8

ChatInput: TextInput: ImageInput: FileReleased May 27, 2026

Built by Anthropic · United States · anthropic.com

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

How to use

Just add the suffix. Hard questions still come back from this model; only easy ones drop to something cheaper, and nothing pricier than it gets used.

model: "anthropic/claude-opus-4.8:auto"

Sets no behavior — whatever your key already stores stays in effect.

Without the suffix, the bare name always goes to this model — no routing, so nothing saved.

Context

1M

Max output

64K

Input $/1M

$5.00

Output $/1M

$25.00

Features

Image inputTool callingJSON

Providers

Anthropic

Providers

Price, latency, and uptime per provider serving this model. Warp tries them in order of how each host has just been behaving, moving to the next on failure. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

GPQA DiamondPhD-level science questions
91.0%
AIMECompetition mathematics
98.3%
FrontierMathResearch-level mathematics
47.2%
SciCodeScientific code generation
53.5%
ARC-AGI-2Abstract reasoning
72.1%
SimpleQA VerifiedFactual accuracy
39.5%

At each model's best reasoning effort

Agent arenaRank on real tool-using sessions (frontier models only)#3+9.28%
Category ranksAmong all rated models
Agent#3Coding#13Korean#13Instruction following#11

Source: LMArena

Speed

Loading provider metrics…

Parameter support

What Warp actually does with each parameter when you call this model. The answer differs by serving provider and by API surface.