Short answer
Claude Opus 4.8 is available through APIVAI at $1.74 per million input tokens and $8.69 per million output tokens as of 2026-10-07, 65% below Anthropic's official list price of $5.00 / $25.00. Use the model ID claude-opus-4-8 with an APIVAI key in the Anthropic Messages format at https://api.apivai.com (Claude Code, Anthropic SDK) or the OpenAI format at https://api.apivai.com/v1. Billing is pay-as-you-go from a prepaid balance, from $10, with no subscription.
Claude Opus 4.8 API pricing
| Per 1M tokens | APIVAI | Official list price |
|---|---|---|
| Input | $1.74 | $5.00 |
| Output | $8.69 | $25.00 |
Prompt caching: cache writes cost $2.18 and cache reads $0.18 per million tokens. Context window: 1M tokens. Prices are checked against the price list every 6 hours; see all model prices.
How much does Claude Opus 4.8 cost per request?
Each request is billed for its input and output tokens. Coding agents resend the conversation and files with every step, so their requests are much larger than a chat message.
| Example | Input / output tokens | APIVAI | Official price |
|---|---|---|---|
| One chat message | 2,000 / 500 each | $0.00783 | $0.0225 |
| One coding-agent step | 30,000 / 1,500 each | $0.0652 | $0.188 |
| 1,000 chat messages | 2,000 / 500 each | $7.83 | $22.50 |
| A month of agent use (100 steps a day, 22 days) | 30,000 / 1,500 each | $144 | $413 |
Thinking is on by default and thinking tokens are billed as output, so the real output count can be higher than the text you see.
How do you call Claude Opus 4.8?
cURL (OpenAI format)
curl https://api.apivai.com/v1/chat/completions \
-H "Authorization: Bearer $APIVAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-8",
"max_tokens": 4096,
"messages": [{"role": "user", "content": "Hello!"}]
}'Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(api_key="YOUR_APIVAI_API_KEY", base_url="https://api.apivai.com/v1")
resp = client.chat.completions.create(
model="claude-opus-4-8",
max_tokens=4096,
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Claude Code and the Anthropic SDK
# macOS / Linux export ANTHROPIC_BASE_URL="https://api.apivai.com" export ANTHROPIC_AUTH_TOKEN="YOUR_APIVAI_API_KEY" claude --model claude-opus-4-8
# Python (Anthropic SDK)
import anthropic
client = anthropic.Anthropic(api_key="YOUR_APIVAI_API_KEY", base_url="https://api.apivai.com")
msg = client.messages.create(model="claude-opus-4-8", max_tokens=4096,
messages=[{"role": "user", "content": "Hello!"}])Claude Code and the Anthropic SDK use https://api.apivai.com without /v1; they add /v1/messages themselves. If ANTHROPIC_API_KEY is set in your shell, remove it first. Full setup: Claude Code guide and Claude API proxy.
Other Anthropic models
| Model | Input / output per 1M | Below official price |
|---|---|---|
| Claude Fable 5.1 | $4.21 / $21.02 | 58% |
| Claude Fable 5 | $4.21 / $21.02 | 58% |
| Claude Opus 5 | $1.74 / $8.69 | 65% |
| Claude Opus 4.7 | $1.74 / $8.69 | 65% |
| Claude Opus 4.6 | $1.74 / $8.69 | 65% |
| Claude Opus 5.5 | $1.39 / $6.96 | 65% |
| Claude Sonnet 4.6 | $1.04 / $5.22 | 65% |
| Claude Sonnet 5.5 | $0.69 / $3.47 | 66% |
| Claude Sonnet 5 | $0.69 / $3.47 | 66% |
| Claude Haiku 4.5 | $0.35 / $1.74 | 65% |
Setup guides
FAQ
Is this the same Claude Opus 4.8 model?
Yes. Requests with the model ID claude-opus-4-8 are answered by Claude Opus 4.8; only the price and the way you pay differ.
What is the model ID for Claude Opus 4.8?
claude-opus-4-8. The list of models changes over time, so check GET https://api.apivai.com/v1/models with your key before hard-coding a name.
Which tools can use Claude Opus 4.8?
Claude Code and the Anthropic SDK through https://api.apivai.com, and any OpenAI-compatible tool (Cursor, Cline, Continue, Aider and others) through https://api.apivai.com/v1.
How is Claude Opus 4.8 billed?
Per token, from a prepaid balance: $1.74 per million input tokens and $8.69 per million output tokens, with thinking tokens counted as output. The minimum top-up is $10 and there is no subscription.
How many requests can I send?
Each key allows 60 requests per minute by default; support can raise the limit.
Create an account, top up from $10 and use claude-opus-4-8 with your key.