Claude Opus 4.8 API
Call Claude Opus 4.8 with one TokenMilo API key. Frontier Claude models for complex coding, agents and analysis. Billed per token at 79% below the official Anthropic price.
| Model ID | claude-opus-4-8 |
| Provider | Anthropic |
| Family | Claude Opus |
| Discount | 79% off official |
Claude Opus 4.8 pricing
USD per 1M tokens. Prices updated 2026-11-13.
| TokenMilo | Official Anthropic | |
|---|---|---|
| Input | $1.06 | $5 |
| Output | $5.33 | $25 |
| Cache read | $0.108 | — |
| Cache write (5 min) | $1.33 | — |
| Cache write (1 hour) | $1.33 | — |
1-hour cache writes are billed at the same price as 5-minute writes.
What it costs in practice
| Workload | TokenMilo | Official | You save |
|---|---|---|---|
| 1,000 requests × 2,000 in / 500 out tokens | $4.79 | $22.50 | $17.71 |
| 1,000 requests × 50,000 in / 2,000 out tokens | $63.76 | $300 | $236 |
What Claude Opus 4.8 is good for
- Coding agents (Claude Code, Cline, Cursor)
- Complex debugging and architecture work
- Long documents and data analysis
- Tool use and multi-step workflows
Supported endpoints
| Anthropic Messages · recommended | POST https://api.tokenmilo.com/v1/messages |
| OpenAI Chat Completions | POST https://api.tokenmilo.com/v1/chat/completions |
Base URL and API key are the same for every format. API guide →
Code examples
curl
curl https://api.tokenmilo.com/v1/messages \
-H "x-api-key: $TOKENMILO_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-opus-4-8",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Hello, Claude Opus 4.8!"}]
}'Python
# pip install anthropic
import os, anthropic
client = anthropic.Anthropic(
base_url="https://api.tokenmilo.com",
api_key=os.environ["TOKENMILO_API_KEY"],
)
msg = client.messages.create(
model="claude-opus-4-8",
max_tokens=1024,
messages=[{"role": "user", "content": "Explain prompt caching in one paragraph."}],
)
print(msg.content[0].text)Use Claude Opus 4.8 in your tools
- Claude Code setup — Run Claude Code with a TokenMilo key on macOS, Linux and Windows.
- Cursor setup — Add Claude and GPT models to Cursor with your own key.
- Cline setup (VS Code) — Configure the Cline coding agent with Claude via TokenMilo.
- Cherry Studio setup — Chat with Claude and GPT in the Cherry Studio desktop app.
Other Claude Opus models
- Claude Opus 5.5 — $0.855 / $4.26 · −79%
- Claude Opus 5 — $1.06 / $5.33 · −79%
- Claude Opus 4.7 — $1.06 / $5.33 · −79%
- Claude Opus 4.6 — $1.06 / $5.33 · −79%
More Anthropic models
- Claude Fable 5.2 — $1.79 / $8.95
- Claude Fable 5.1 — $2.23 / $11.18
- Claude Fable 5 — $2.23 / $11.18
- Claude Sonnet 5.5 — $0.423 / $2.13
- Claude Sonnet 5 — $0.423 / $2.13
- Claude Sonnet 4.6 — $0.639 / $3.19
FAQ
Is this the real Claude Opus 4.8?
Yes. Requests with model ID claude-opus-4-8 are served by the genuine Anthropic model — no quantized, swapped or downgraded variant. Response quality is the same as calling Anthropic directly.
How much does Claude Opus 4.8 cost on TokenMilo?
$1.06 per 1M input tokens and $5.33 per 1M output tokens, compared with $5 / $25 officially — 79% less. There is no subscription or monthly minimum.
Which API format should I use for Claude Opus 4.8?
The Anthropic Messages API (https://api.tokenmilo.com/v1/messages) is recommended and supports every Claude feature, including prompt caching, tool use and extended thinking. The OpenAI-compatible Chat Completions endpoint also works for simple chat.
Does Claude Opus 4.8 support prompt caching?
Yes. Cache reads are billed at $0.108 per 1M tokens, which makes long system prompts and coding-agent sessions much cheaper.
Start using Claude Opus 4.8
Sign up, top up, create a key — and point your SDK at TokenMilo.