Claude Opus 4.8 pricing
What Claude Opus 4.8 costs per million tokens, on 3 platforms: input, output, cache read and cache write, with batch and long-context rates where the provider publishes them. Every figure is the rate Vigil's proxy bills with, read from the provider's own page.
Prices checked 9 Oct 2026 against platform.claude.com · registry sources: aws.amazon.com, cloud.google.com. All shown rates agreed with the page.
Claude Opus 4.8 on Anthropic API
Model id claude-opus-4-8. Verified against the provider's published price; registry row retrieved 2026-09-11 from platform.claude.com.
| Applies | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $5.00 | $25.00 | $0.500 | $6.25 5m · $10.00 1h |
USD per 1M tokens. A dash means the provider publishes no rate for that dimension, so the proxy declines to price it.
- Endpoint classes: global, regional (×1.1).
- on_demand: the standard rate.
- batch: 50% below the standard rate.
- fast: 2× the standard rate on input and output; cache rates unpublished.
- No long-context tier: the standard rate applies at any prompt size.
Claude Opus 4.8 on AWS Bedrock
Model id anthropic.claude-opus-4-8. Verified against the provider's published price; registry row retrieved 2026-09-11 from aws.amazon.com.
| Applies | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $5.00 | $25.00 | $0.500 | $6.25 5m · $10.00 1h |
USD per 1M tokens. A dash means the provider publishes no rate for that dimension, so the proxy declines to price it.
- Endpoint classes: global, regional (×1.1).
- on_demand: the standard rate.
- batch: 50% below the standard rate.
- provisioned: capacity-billed (PTU/GSU/provisioned throughput) — per-token math fabricates a number (§10.6).
- Above 200,000 input tokens the rate is unverified, so the proxy declines to price such a call rather than guess.
Claude Opus 4.8 on Google Vertex AI
Model id claude-opus-4-8. Verified against the provider's published price; registry row retrieved 2026-09-11 from cloud.google.com.
| Applies | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $5.00 | $25.00 | $0.500 | $6.25 5m · $10.00 1h |
USD per 1M tokens. A dash means the provider publishes no rate for that dimension, so the proxy declines to price it.
- Endpoint classes: global, regional (×1.1), multi_region (×1.1).
- on_demand: the standard rate.
- batch: 50% below the standard rate.
- provisioned: capacity-billed (PTU/GSU/provisioned throughput) — per-token math fabricates a number (§10.6).
- Above 200,000 input tokens the rate is unverified, so the proxy declines to price such a call rather than guess.
Price a Claude Opus 4.8 call
Claude Opus 4.8 on Anthropic API, standard rate, priced now
Cache writes, batch, endpoint class and monthly volume: AI token calculator
Questions
- Is Claude Opus 4.8 the same price on AWS Bedrock and Google Vertex AI as on Anthropic API?
- Yes. The input, output and cache-read rates the registry holds for Anthropic API, AWS Bedrock, Google Vertex AI are the same per 1M tokens on the global endpoint class. A regional or multi-region endpoint, where one is published, carries its own factor (shown per platform below).
- What does a cache read cost on Claude Opus 4.8?
- A cache-read token on Anthropic API costs $0.500 per 1M tokens, against $5.00 for an ordinary input token. An ordinary input token costs 10 times as much. A cache write costs $6.25 (5m) or $10.00 (1h) per 1M tokens.
- Does Claude Opus 4.8 have a batch price?
- Yes: batch: 50% below the standard rate. The batch rate applies to the whole request; the proxy prices a batch call from the same row with that factor applied.
Other models: Claude Opus 5 · Claude Sonnet 5 · Claude Haiku 4.5 · Claude Fable 5.1 · Claude Sonnet 4.6 · GPT-6 Sol · GPT-6 Luna · GPT-5.6 Sol · GPT-5.6 Terra · GPT-5.3 Codex · GPT-4o · GPT-4o mini · Gemini 3.1 Pro · Gemini 3.5 Flash · Gemini 3.8 Flash · DeepSeek V4 Pro · DeepSeek Flash · Grok 4.6 · Kimi K3