RETIRED AUG 5 2026200K CONTEXTTEXT + VISIONPROMPT CACHINGBATCH -50%
Claude Opus 4.1 API Pricing
Claude Opus 4.1 was retired by Anthropic on August 5, 2026 - the claude-opus-4-1-20250805 model id no longer answers. Anthropic names Claude Opus 4.8 as the replacement. Its last listed rates were $15.00/M input and $75.00/M output, with cache hits at $1.50/M, kept here for invoice checks and migration math. Checked against Anthropic's model deprecations page.
Input - per 1M tokens
$15.00/M
Stable Anthropic table flat
Output - per 1M tokens
$75.00/M
Stable since launch flat
Cached input - 90% off
$1.50/M
Cache 5min or 1h -90%
Effective - agentic blend
$10.24/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with Claude Opus 4.1 rates. Tweak spend, output mix, or cache hit rate; share the URL to share the calculation.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CODING AGENT
Repo-wide bug fix
$0.898/task
LONG DOC ANALYSIS
Reading 100-page contracts
$1.41/doc
RAG SUPPORT
Support agent ticket triage
$0.093/ticket
ASSISTANT
Research planning turn
$0.205/turn
Estimate · anthropic-bpe-estimate · ≈3.5 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters 354
Words 58
Tokens (estimated) 101 tokens
Cost as input · uncached $0.00152 USD
Cost as output · uncached $0.00758 USD
Cost as cached input $0.00015 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Claude Opus 4.7 | $5.00 cache $0.50 | $25.00 | $3.41 −3.0× | 1M | Frontier reasoning and hard code |
| Claude Opus 4.6 | $5.00 cache $0.50 | $25.00 | $3.41 −3.0× | 1M | Frontier reasoning and hard code |
| Claude Opus 4.5 | $5.00 cache $0.50 | $25.00 | $3.41 −3.0× | 200K | Frontier reasoning and hard code |
| Claude Opus 4.1 Current | $15.00 cache $1.50 | $75.00 | $10.24 agentic 92/8 | 200K | Legacy Opus workloads |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $2.05 −5.0× | 1M | Production agents and coding |
| Claude Sonnet 4.5 | $3.00 cache $0.30 | $15.00 | $2.05 deprecated · −5.0× | 200K | Production agents and coding |
| Claude Haiku 4.5 | $1.00 cache $0.10 | $5.00 | $0.682 −15× | 200K | Support and classification |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 −5.7× | 1.05M | Tool use and app agents |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 −21× · promo | 1M | Long-context document analysis |
Frequently asked.
Practical pricing questions, with vendor list prices separated from workload assumptions.
Q · 01 Can I still call Claude Opus 4.1? +
No. Anthropic retired
claude-opus-4-1-20250805 on August 5, 2026, and requests to it now fail. Anthropic names Claude Opus 4.8 as the replacement. The rates on this page are the last ones Anthropic listed, kept for reading old invoices and for estimating a migration.Q · 02 What is Claude Opus 4.1 priced at? +
Anthropic's pricing page lists
$15/M input, $75/M output, and $1.5/M cache-hit input for Claude Opus 4.1. Under the 92/8 agentic blend with 82% cache hits, that works out to $9.616/M.Q · 03 How does prompt caching change the price? +
Cache hits are listed at
$1.5/M, which is 10% of the $15/M base input rate. Anthropic also charges cache writes at $18.75/M for 5-minute writes and $30/M for 1-hour writes. The calculator models repeated prompt sections as cache hits.Q · 04 Is there a Batch API discount? +
Yes. Anthropic's Batch API gives a 50% discount on input and output tokens. For Claude Opus 4.1, the batch table maps to
$7.5/M input and $37.5/M output.Q · 05 Does long context cost extra? +
This page uses the model's documented
200K context label. Longer-context Opus 4.6, Opus 4.7, and Sonnet 4.6 use standard pricing across the full 1M window. Prompt caching and batch discounts still apply according to their normal rules.Q · 06 Does regional pricing differ? +
Anthropic says earlier models do not support the
inference_geo parameter and use standard first-party API pricing. Bedrock and Vertex AI publish their own regional pricing policies.Q · 07 Are volume discounts published? +
No fixed public volume-discount ladder is published. Enterprise and committed-spend contracts can have private terms, but standard API users should assume the list prices shown here unless they have a separate agreement.
Q · 08 How accurate is the tokenizer estimate? +
The live counter uses a Claude-family English estimate of
4.875 characters per token. Actual billing uses Anthropic's server-side tokenizer; code, tables, and non-English text can differ materially.