LLM Reference
Anthropic

Claude Opus 4.8 on Anthropic

Claude 4.8 · Anthropic

Serverless

Last refreshed 2026-07-26. Next refresh: weekly.

Why use Claude Opus 4.8 on Anthropic?

Anthropic offers Claude Opus 4.8 with pay-as-you-go pricing at $5.00/1M input tokens. Anthropic is a safety-focused AI research company and creator of the Claude model family, offering API access through the Anthropic Console for text generation, analysis, and coding tasks.

Compare Claude Opus 4.8 across 6 providers to find the best fit for your use case
Input / 1M
$5.00
Output / 1M
$25.00
Cache
read $0.50 / 5m $6.25 / 1h $10.00
Batch
-50% · in $2.50 / out $12.50

Setup recipe

Python + curl
Install
pip install anthropic
Auth
export ANTHROPIC_API_KEY=...
Call
import anthropic
client = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY from env
message = client.messages.create(
    model="claude-opus-4-8",
Model ID
claude-opus-4-8

Request example

import anthropic

client = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY from env
message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

Gotchas

  • Use the versioned model ID, e.g. "claude-sonnet-4-6" or "claude-opus-4-7-20251101".
  • The examples expect ANTHROPIC_API_KEY; rename it only if your application config maps the new variable.

Compare Claude Opus 4.8 Across Providers

ProviderInput (per 1M)Output (per 1M)
Anthropic$5.00$25.00
AWS Bedrock
GCP Vertex AI
Microsoft Foundry
OpenRouter$5.00$25.00
View all 6 providers →

Pricing

TypePrice (per 1M)
Input tokens$5.00
Output tokens$25.00
Query$10.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API

About Claude Opus 4.8

Claude Opus 4.8 is Anthropic's flagship Claude 4.8 model, released May 28, 2026 for agentic coding, long-horizon reasoning, computer use, and professional knowledge work. It supports text and image inputs, adaptive reasoning, tool use, structured outputs, computer-use tools, prompt caching, Batch API, Dynamic Workflows parallel subagents, a 1M-token context window on Anthropic API/Bedrock/Vertex, and 128K max output. Key datapack rows: SWE-bench Pro 69.2%, SWE-bench Verified 88.6%, Terminal-Bench 2.1 74.6%, HLE with tools 57.9%, OSWorld-Verified 83.4%, GDPval-AA 1890 Elo, and MCP-Atlas 82.2%. Standard Anthropic API pricing is $5/M input and $25/M output.

Get Started

Model Specs

Released2026-05-28
Context1m
ArchitectureDecoder Only
Knowledge cutoff2026-01