Claude Opus 4.8

Claude Opus 4.8 is the previous Opus flagship — highly autonomous, strong on long-horizon agentic work, knowledge work and memory, with a noticeably warmer and less hedged writing voice than 4.7. Same request surface as Opus 5 minus the two Opus 5 breaking changes, which makes it the usual fallback target when a newer model declines a request.

Input / output price: From $5 / $25 per 1M
Context: 1M tokens
Max output: 128K tokens

index.ts

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.onefoldhq.com/v1",
  apiKey: process.env.ONEFOLD_API_KEY,
});

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(result.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.onefoldhq.com/v1",
  apiKey: process.env.ONEFOLD_API_KEY,
});

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(result.choices[0].message.content);

main.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.onefoldhq.com/v1",
    api_key=os.environ["ONEFOLD_API_KEY"],
)

result = client.chat.completions.create(
    model="anthropic/claude-opus-4-8",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
)

print(result.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.onefoldhq.com/v1",
    api_key=os.environ["ONEFOLD_API_KEY"],
)

result = client.chat.completions.create(
    model="anthropic/claude-opus-4-8",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
)

print(result.choices[0].message.content)

request.sh

curl https://api.onefoldhq.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4-8",
    "messages": [{ "role": "user", "content": "Why is the sky blue?" }]
  }'

curl https://api.onefoldhq.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4-8",
    "messages": [{ "role": "user", "content": "Why is the sky blue?" }]
  }'

Playground

Try out Claude Opus 4.8 by Anthropic. Usage is billed to your team at API rates.

Claude Opus 4.8

Message Claude Opus 4.8

Providers

Route to any available provider. One request shape for all of them, and the router picks on price, health and latency.

Provider	Context	Max output	Latency	Throughput	Input	Output	Cache
AnthropicLegal: Terms · Privacy	1M	128K	0.8 s	46 tps	$5/M	$25/M	Read$0.50/MWrite$6.25/M
BedrockLegal: Terms · Privacy	1M	8K	1.7 s	53 tps	$5/M+3 more	$25/M+3 more	Read$0.50/MWrite$6.25/M
Google Vertex AILegal: Terms · Privacy	1M	8K	1.1 s	45 tps	$5/M+3 more	$25/M+3 more	Read$0.50/MWrite$6.25/M

Uptime 24 hours

Direct request success rate on Onefold and per-provider. Visit the docs for more info.

Sep 10, 8:45 PMSep 11, 8:30 PM

Uptime
Series	Low	Typical	High
Onefold	100.00%	100.00%	100.00%
Anthropic	91.23%	99.69%	99.97%
Bedrock	95.21%	99.77%	99.98%
Google Vertex AI	99.63%	99.96%	99.98%

1Onefold100.00%
2Google Vertex AI99.96%
3Bedrock99.77%
4Anthropic99.69%

Status 24 hours

Reliability of providers. Visit the docs for more info.

Onefold100.00%
Anthropic99.69%
Bedrock99.77%
Google Vertex AI99.96%

Sep 10, 8:45 PMSep 11, 8:30 PM

Status of Onefold and its providers over the last 24 hours
Provider	Uptime	Operational windows	Degraded windows	Outage windows
Onefold	100.00%	96	0	0
Anthropic	99.69%	91	4	1
Bedrock	99.77%	90	6	0
Google Vertex AI	99.96%	96	0	0

Throughput 24 hours

P50 throughput on live gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Sep 10, 8:45 PMSep 11, 8:30 PM

Throughput
Series	Low	Typical	High
Anthropic	58.18 tps	62.02 tps	69.56 tps
Bedrock	46.89 tps	49.20 tps	52.65 tps
Google Vertex AI	55.75 tps	56.79 tps	60.63 tps

1Anthropic62.02 tps
2Google Vertex AI56.79 tps
3Bedrock49.20 tps

Latency 24 hours

P50 time to first token (TTFT) on live gateway traffic, in seconds. View the docs for more info.

Sep 10, 8:45 PMSep 11, 8:30 PM

Latency
Series	Low	Typical	High
Anthropic	1.05 s	1.19 s	1.27 s
Bedrock	0.74 s	0.78 s	0.84 s
Google Vertex AI	1.30 s	1.44 s	1.55 s

1Bedrock0.78 s
2Anthropic1.19 s
3Google Vertex AI1.44 s

Pricing with caching

What input tokens cost as more of your prefix is reused. Cached input bills at $0.50 per million instead of $5.

Chart requires JavaScript. The figures are in the table below.

Blended input rate
List price

View as table

Blended input price for Claude Opus 4.8 by cache hit ratio
Cache hit ratio	0%	25%	50%	75%	90%
Blended input rate	$5	$3.88	$2.75	$1.63	$0.95
List price	$5	$5	$5	$5	$5

Cache hit ratio	Blended input	Saving	1M in + 1M out
0%	$5/M	—	$30
25%	$3.88/M	22%	$28.88
50%	$2.75/M	45%	$27.75
75%	$1.63/M	68%	$26.63
90%	$0.95/M	81%	$25.95

Getting started

Call Claude Opus 4.8 through Onefold with any OpenAI-compatible client by changing the base URL. Onefold authenticates the request and routes it to an available provider.

index.ts

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.onefoldhq.com/v1",
  apiKey: process.env.ONEFOLD_API_KEY,
});

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(result.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.onefoldhq.com/v1",
  apiKey: process.env.ONEFOLD_API_KEY,
});

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(result.choices[0].message.content);

Streaming

Stream tokens as they are produced. The gateway never buffers the upstream response.

stream.ts

const stream = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Summarise this document." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

const stream = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [{ role: "user", content: "Summarise this document." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Describe this image." },
        { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
      ],
    },
  ],
});

const result = await client.chat.completions.create({
  model: "anthropic/claude-opus-4-8",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Describe this image." },
        { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
      ],
    },
  ],
});

Top-level parameters

The same Claude Opus 4.8 request in every API format Onefold supports.

Parameter	Type	Required	Description
model	string	Yes	Model id in the form `creator/model`, here `anthropic/claude-opus-4-8`. Onefold routes the request to an available provider.
messages	Message[]	Yes	The conversation so far. System, user, assistant and tool roles are all accepted and translated into the provider dialect.
max_tokens	number	No	Hard cap on generated tokens. Claude Opus 4.8 supports up to `128,000`. Thinking tokens count toward this limit.
stream	boolean	No	Stream the response as server-sent events. The gateway streams byte by byte rather than buffering the upstream response.
tools	Tool[]	No	Tool definitions in OpenAI shape. Translated into the provider native format, including parallel tool calls.

Input limits

Input	Formats	Sources	Limits
Text	—	—	Prompt and response share the 1M-token context window
Image	png, jpeg, webp, gif	URL, base64	Sent as image parts in messages; counts as input tokens
PDF	pdf	URL, base64	Sent as file parts in messages; counts as input tokens

Capabilities

Streaming
Tool use
Vision
High-res vision
PDF input
Citations
Structured outputs
Adaptive thinking
Effort control
Task budgets
Fast mode
Prompt caching
Compaction
Batch API
1M context

Accepted parameters

max_tokens
stream
stop_sequences
system
tools
tool_choice
thinking
effort
output_config.format
speed

Specification

Model id: anthropic/claude-opus-4-8
Upstream id: claude-opus-4-8
Modalities: Text, Image in · Text out
Context window: 1,000,000 tokens
Max output: 128,000 tokens
API dialect: anthropic, translated for you
Knowledge cutoff: Jan 2026
Min cacheable prefix: 1,024 tokens
Available on: Anthropic, Bedrock, Google Vertex AI

Similar models

Switch between any of them by changing the model string.

Model	Context	Input	Output
anthropic/claude-opus-5	1M	$5/M	$25/M
anthropic/claude-opus-4-7	1M	$5/M	$25/M
anthropic/claude-opus-4-6	1M	$5/M	$25/M

About Claude Opus 4.8

It speaks the anthropic dialect and reaches 3 platforms through Onefold. Its knowledge is most reliable through Jan 2026.

What to consider when choosing a provider

Output ceiling: platforms cap output independently of the model. Anthropic allows 128K. Bedrock allows 8K. Google Vertex AI allows 8K.
Authentication: Onefold authenticates requests with one key. You do not manage provider credentials directly.
Dialect: this model speaks anthropic. You never write it — the gateway accepts OpenAI-shaped requests and translates at the edge.

When to use Claude Opus 4.8

Best for

Teams already tuned on the Opus 4 series who want the ceiling without a prompt rewrite.
Variable reasoning depth: tune effort per request rather than per model
Long-context work: 1M tokens in one window
Agentic tool use: parallel tool calls, translated to the native format

Consider alternatives when

Latency dominates: a lighter model in the same family answers sooner
The task is narrow: a smaller model hits the same bar for less on well-scoped work

Frequently asked questions

What does Claude Opus 4.8 cost?

$5 per million input tokens and $25 per million output tokens, which is Anthropic's published list price. Onefold adds a flat 5% routing fee on top, billed from prepaid credits. Cached input is far cheaper at $0.50 per million tokens.

What is the context window for Claude Opus 4.8?

1,000,000 tokens of context, with up to 128,000 tokens in a single response. Its knowledge is most reliable through Jan 2026.

How do I call Claude Opus 4.8?

Point any OpenAI-compatible client at https://api.onefoldhq.com/v1 and pass "anthropic/claude-opus-4-8" as the model string. There is no SDK to install, we translate the request into Anthropic's anthropic dialect on the way out and the response stream back on the way in.

How is prompt caching billed?

Reading from cache costs $0.50 per million tokens, one tenth of the list input price. Writing to a five-minute cache costs $6.25 (1.25× list), and a one-hour cache costs $10 (2× list). Prefixes shorter than 1,024 tokens will not cache at all.

Which API dialect does Claude Opus 4.8 speak?

The anthropic dialect. You never write it: the gateway accepts OpenAI-shaped requests and translates them at the edge, streaming byte by byte rather than buffering. Switching to a model on a different dialect means changing the model string and nothing else.

Is Claude Opus 4.8 being retired?

No retirement date has been announced. Anthropic publishes deprecations ahead of time, and this page tracks that field, so a date will appear here if one is set.