Claude Opus 4.8 pricing, context window and limits
Claude Opus 4.8 costs $5 per million input tokens and $25 per million output tokens at Anthropic list price. It accepts up to 1,000,000 tokens of context and returns up to 128,000 tokens.
- Model id
claude-opus-4-8 - Snapshot
What does Claude Opus 4.8 cost?
| Input | $5 |
|---|---|
| Output | $25 |
| Cached input (read) | $0.5 |
| Cache write | $6.25 |
US dollars per million tokens. A dash means no price is published.
How much can Claude Opus 4.8 read and write?
| Context window | 1,000,000 |
|---|---|
| Max output | 128,000 |
What can Claude Opus 4.8 do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, pdf |
| Output | text |
What does a request to Claude Opus 4.8 cost?
| A typical request: 1,000 tokens in, 500 out | $0.018 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.075 |
| 1,000 typical requests | $17.5 |
| 1 million tokens in and 1 million out | $30 |
Input read from the provider's prompt cache costs $0.5 per million tokens instead of $5, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.013 instead of $0.018.
Among 17 Anthropic models with a published price, Claude Opus 4.8 is the 10th cheapest by input price. Its context window is the largest of 17. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Claude Opus 4.8 through DVARA?
Configure the anthropic provider in the DVARA LLM Gateway and send the model id claude-opus-4-8. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Anthropic models are there?
- Claude Opus 4.7$5 in · $25 out · 1M context
- Claude Opus 5$5 in · $25 out · 1M context
- Claude Opus 4.6$5 in · $25 out · 1M context
- Claude Opus 5.5$4 in · $20 out · 1M context
- Claude Opus 4.5$5 in · $25 out · 200K context
- Claude Sonnet 4.5 (latest)$3 in · $15 out · 200K context
- Claude Opus 4.5 (latest)$5 in · $25 out · 200K context
- Claude Sonnet 4.5$3 in · $15 out · 200K context
- Claude Haiku 5.5$0.1 in · $0.5 out · 1M context
- Claude Sonnet 4.6$3 in · $15 out · 1M context
- Claude Haiku 4.5$1 in · $5 out · 200K context
- Claude Sonnet 5$2 in · $10 out · 1M context
Which models from other providers are similar to Claude Opus 4.8?
These are the closest in context window and input price, one per provider.
- Claude Opus 4.7Amazon Bedrock · $5 in · $25 out · 1M context
- GPT-5.5OpenAI · $5 in · $30 out · 1.05M context
- Qwen Deep ResearchAlibaba Qwen · $7.742 in · $23.367 out · 1M context
- Kimi K3Moonshot AI · $3 in · $15 out · 1.05M context
- Gemini 3.1 Pro PreviewGoogle Gemini · $2 in · $12 out · 1.05M context