Claude Opus 4.8

Anthropic's latest Opus model with stronger agentic coding, long-context work, and advanced reasoning capabilities.

Input price: $5.50–$6.05
Output price: $27.50–$30.25

Context: 1M
Max output: 128K

Capability: 160 (#19 of 79)
Human preference: 1454
30-day uptime: —

Released: 2026-05-28
Knowledge cutoff: 2026-01

InputTextImagePDFOutputText

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

AutoInput$5.50–$6.05Output$27.50–$30.25Cache read$0.55–$0.605Context1MMax output128KWe send each request to the best-priced healthy provider. You pay that provider’s price.AnthropicInput$5.50Output$27.50Cache read$0.55United StatesNo trainingNo retentionAnthropic (AWS)Input$5.50Output$27.50Cache read$0.55United StatesAmazon BedrockInput$6.05Output$30.25Cache read$0.605Context1MMax output128KUnited StatesNo trainingNo retention

Pricing

Prices vary by provider. Showing Anthropic, the lowest. Pick a provider above to see its prices.

Item	Standard	fast
Inputper 1M tokens	$5.50	$11.00
Outputper 1M tokens	$27.50	$55.00
Cache readper 1M tokens	$0.55	$1.10
Cache write (5 min)per 1M tokens	$6.875	$13.75
Cache write (1 hour)per 1M tokens	$11.00	$22.00
Batch inputper 1M tokens	$2.75	—
Batch outputper 1M tokens	$13.75	—
Web searchper request	$0.011	$0.011

Try it

Runs on your balance and is billed like any API request.

curl https://api.ohmygpt.com/v1/messages \
  -H "x-api-key: $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "anthropic/claude-opus-4-8",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

import os

from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["OHMYGPT_API_KEY"],
    base_url="https://api.ohmygpt.com",
)

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

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OHMYGPT_API_KEY,
  baseURL: "https://api.ohmygpt.com",
});

const message = await client.messages.create({
  model: "anthropic/claude-opus-4-8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
for (const block of message.content) {
  if (block.type === "text") console.log(block.text);
}

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

Better value: more capable, lower price
Pareto frontier
This model
Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-10), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

Claude Opus 4.8This model

Capability: 160
Input: $5.50–$6.05
Output: $27.50–$30.25

Claude Opus 5

Capability: 164
Input: $5.50–$6.05
Output: $27.50–$30.25

GPT-5.5

Capability: 160
Input: $4.50–$9.00
Output: $27.00–$40.50

Kimi K3.1 Pro HighSpeed

Capability: 162
Input: $4.1756
Output: $21.8416

Ember-1

Capability: —
Input: $3.00
Output: $15.00

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-09): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text