Anthropic

Claude Opus 4.8 (batch)

by Anthropictext+image+file->text1 endpoint

Overview

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 context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Stop sequences

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
1M tokens
Max Output
128K tokens
Tokenizer
Claude
Content Moderation
Enabled

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity

Pricing

Per 1M tokens
Input$2.50
Output$12.50
Cache read$0.25
Cache write$3.13
Added
May 27, 2026
Last synced 9/18/2026