Skip to content
OpenKey

Claude Opus 4.8

AnthropicReleased May 27, 2026

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...

Try in playground
Context window
1M tokens
Max output
128K tokens
Input
text, image, file
Output
text
Tokenizer
Claude
Released
May 27, 2026
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$5.00$0.150$5.15
Output$25.00$0.750$25.75
Cache read$0.500$0.015$0.515
Cache write$6.25$0.188$6.44

Benchmarks

Artificial Analysis

Intelligence index
55.7
Coding index
74.3
Agentic index
47.2

Design Arena

CategoryEloWin rateRank
agenticgamedevagents126963.9%#2
agentichtmlslidesagents122755.6%#4
agenticslidesagents129464.8%#2
agenticslides(html)agents123056%#4
agenticslides(python-pptx)agents131068.9%#2
androidnativeagents134368.6%#1
Full-stackagents133467%#2
htmlslidesagents122455.7%#4
Mobile appsagents128058.6%#1
pptxslidesagents130667.9%#2
python-pptxslidesagents129865.9%#2
Web appsagents129355.8%#2
3Dmodels128656.3%#21
ASCII artmodels130162.5%#7
Codemodels128254.9%#21
Data vizmodels127755.3%#17
Game devmodels130054.7%#14
SVGmodels123654.1%#17
UI componentsmodels128755.4%#20
Websitesmodels128155%#21

Head-to-head preference voting. How we filter and rank

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • stop
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model anthropic/claude-opus-4.8.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.8",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="anthropic/claude-opus-4.8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "anthropic/claude-opus-4.8",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Claude Opus 4.8 cost via API?
Through OpenKey, Claude Opus 4.8 costs $5.15 per 1M input tokens and $25.75 per 1M output tokens. That is the provider price ($5.00 / $25.00) plus a flat 3% fee — nothing else.
What is Claude Opus 4.8's context window?
Claude Opus 4.8 accepts up to 1M tokens of context and returns up to 128K tokens per request.
Is Claude Opus 4.8 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "anthropic/claude-opus-4.8" using any OpenAI SDK — only the base URL and API key change.
What inputs does Claude Opus 4.8 support?
Claude Opus 4.8 accepts text, image, file input and produces text output.

More from Anthropic

All Anthropic models →