Claude Opus 4.8

Anthropic · Flagship Models

#256.0

Claude Opus 4.8 is Anthropic's reasoning-capable model: $5/$25 per 1M input/output tokens, 1M token context window, 69.2% on SWE-Bench Pro. It supports native tool calling, extended reasoning, image/file input. Released 2026-05-28.

Verified · 2+ sourcesVerified Jun 10, 2026MultimodalLong Context

Input Price

$5

Output Price

$25

Cache Read Price

$0.5

Context Window

1M

All metrics

MetricValueProvenance receipt
Input Price$5
Output Price$25
Cache Read Price$0.5
Context Window1M
Max Output Tokens128K
SWE-Bench Pro Score69.2%
Tool CallingYes
Extended ReasoningYes

Pricing

Pay-as-you-go API

$5per 1M input tokens

Output
$25 / 1M tokens
Cache read
$0.5 / 1M tokens
Verified · 2+ sourcesChecked Jun 10, 2026
Official pricing →

Data sources

Facts on this page are sourced from the following verified sources.

All sources are verified before data goes live.

Compare Claude Opus 4.8

Related models

#3GPT-5.5

OpenAI

52.5

GPT-5.5 is OpenAI's reasoning-capable model: $5/$30 per 1M input/output tokens, 1.1M token context window, 58.6% on SWE-Bench Pro.

#4DeepSeek V4 Pro

DeepSeek

51.8

DeepSeek V4 Pro is DeepSeek's reasoning-capable model: $0.43/$0.87 per 1M input/output tokens, 1M token context window, 18% on SWE-Bench Pro.

#5Gemini 3.1 Pro Preview

Google

50.8

Gemini 3.1 Pro Preview is Google's reasoning-capable model: $2/$12 per 1M input/output tokens, 1.0M token context window, 54.2% on SWE-Bench Pro.

#8Kimi K2.6

Moonshot AI

32.9

Kimi K2.6 is Moonshot AI's reasoning-capable model: $0.95/$4 per 1M input/output tokens, 262K token context window, 27.3% on SWE-Bench Pro.

#10GPT-5.5 Pro

OpenAI

31.9

GPT-5.5 Pro is OpenAI's reasoning-capable model: $30/$180 per 1M input/output tokens, 1.1M token context window.

#11Qwen3.7 Max

Alibaba

31.7

Qwen3.7 Max is Alibaba's reasoning-capable model: $2.50/$7.50 per 1M input/output tokens, 1M token context window.

Spotted an error? Suggest a correction.