Input
- Official Anthropic
- $5
- Here (−50%)
- $2.5
claude-opus-4-8
Claude Opus 4.8 API — price per token
Claude Opus 4.8 is Anthropic's most capable Opus-tier model — the default choice for agentic coding, long-horizon tasks and hard reasoning. Here is what it costs per token, and how to run it cheaper on the same API.
Pricing per 1M tokens
| Rate | Official Anthropic | Here (−50%) |
|---|---|---|
| Input | $5 | $2.5 |
| Output | $25 | $12.5 |
| Cache read | $0.5 | $0.25 |
| Cache write (5m) | $6.25 | $3.125 |
Output
- Official Anthropic
- $25
- Here (−50%)
- $12.5
Cache read
- Official Anthropic
- $0.5
- Here (−50%)
- $0.25
Cache write (5m)
- Official Anthropic
- $6.25
- Here (−50%)
- $3.125
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1M tokens. Max output: 128K tokens.
Best for
- Agentic coding in Claude Code, Cursor and Cline.
- Long-horizon autonomous tasks and complex refactors.
- The hardest reasoning, planning and review work.
Good to know
- Adaptive thinking is the recommended mode; thinking tokens bill as output.
- 1M-token context window at standard pricing — no long-context premium.
How to use Claude Opus 4.8
Create a free account, generate one key, and point any Anthropic-compatible tool at https://router.apitoken.sale with model ID claude-opus-4-8. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://api.apitoken.sale keep working.
Frequently asked questions
How much does the Claude Opus 4.8 API cost?
Officially $5 per 1M input tokens and $25 per 1M output tokens. On apiToken.sale the same requests cost 50% less — $2.50/$12.50 at the flat discount applied to every call.
What is the model ID for Claude Opus 4.8?
claude-opus-4-8. Use it unchanged with the Anthropic SDK, Claude Code, Cursor or any compatible tool pointed at https://router.apitoken.sale.
Is Opus 4.8 worth the price over Sonnet?
For hard agentic and reasoning work, usually yes. For routine coding, Sonnet 5 delivers near-Opus quality at 40% of the token price — many teams route by task.
Run Claude Opus 4.8 on the same Anthropic API at a flat 50% off — instant key, prepaid balance, card or crypto.