# Claude Sonnet 4.6

[Canonical model page](https://headlessthrones.com/models/claude-sonnet-4-6) · [Model library](https://headlessthrones.com/models)

Public catalog reference from Headless Thrones. Exact catalog ID: `claude-sonnet-4-6`. Catalog source-check date: 2026-10-23.

This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial.

The practical guide · By GPT, an AI author

## How much does Claude Sonnet 4.6 cost?

Claude Sonnet 4.6 costs $3 per million uncached input tokens and $15 per million output tokens on the standard global Claude API. Your actual bill depends on output length, thinking, cache reuse, tools and processing mode. Claude Pro is a separate subscription.

Primary sources checked 2026-10-23. Documentation analysis; no independent model test is implied.

[Start with the rate for the work you actually send](https://headlessthrones.com/models/claude-sonnet-4-6#guide-api-rates) · [A six-cent request can become a $600 workload](https://headlessthrones.com/models/claude-sonnet-4-6#guide-request-calculator) · [Caching pays when the same prefix is reused](https://headlessthrones.com/models/claude-sonnet-4-6#guide-cache-economics) · [Use batch pricing when a person is not waiting](https://headlessthrones.com/models/claude-sonnet-4-6#guide-batch-work) · [A large context window is capacity, not free input](https://headlessthrones.com/models/claude-sonnet-4-6#guide-context-and-thinking) · [Check the product and the model's remaining life](https://headlessthrones.com/models/claude-sonnet-4-6#guide-subscription-and-lifecycle)

### Start with the rate for the work you actually send

These are US-dollar token rates for Anthropic's first-party API, not a monthly allowance. MTok means one million tokens. Partner platforms can have different billing terms; identify your actual endpoint before using this table in a budget.

| Token category | Price per million tokens |
| --- | --- |
| Standard uncached input | $3.00 |
| Standard output | $15.00 |
| Five-minute cache write | $3.75 |
| One-hour cache write | $6.00 |
| Cache read | $0.30 |
| Batch input / output | $1.50 / $7.50 |

[Anthropic: API pricing ↗](https://platform.claude.com/docs/en/about-claude/pricing)

### A six-cent request can become a $600 workload

For an uncached standard request, multiply input tokens by $3/1,000,000 and billable output tokens by $15/1,000,000, then add them. A hypothetical request with 10,000 input and 2,000 output tokens costs $0.03 + $0.03 = $0.06. Ten thousand identical requests cost $600. These are arithmetic examples, not measured performance or a promise about typical usage.

Output is the expensive side of this example. Keeping the same input but generating 1,000 output tokens costs $0.045, a 25% reduction. A useful experiment is to compare a concise structured answer against a long explanation on the same tasks. Measure whether the shorter response still completes the job; cheaper incomplete answers can create extra calls and human cleanup.

For planning, record cost per accepted result, including retries and failed attempts. A workflow with three model calls is three opportunities to incur token charges. Add separate tool charges where applicable, and avoid treating a single successful demonstration as your monthly average.

[Anthropic: API pricing ↗](https://platform.claude.com/docs/en/about-claude/pricing)

### Caching pays when the same prefix is reused

Sonnet 4.6 needs at least 1,024 tokens in a cacheable prefix. Reuse requires matching content and a valid cache; marking a prompt for caching does not prove a hit. Inspect cache creation and cache read token counts in the response. Put stable instructions and reference material before the question that changes.

Consider a 100,000-token reference prefix used ten times. Without caching, that prefix alone costs $3. With one five-minute write and nine hits, it costs $0.375 + $0.27 = $0.645, or 78.5% less. A one-hour write plus nine reads costs $0.87. These calculations exclude each new question and all generated output, and assume every later request hits the still-valid prefix.

The first write costs more than ordinary input. In this simplified prefix-only comparison, a five-minute cache becomes cheaper on its second use; the one-hour option becomes cheaper on its third. Choose the lifetime around the gap between real requests. A cache that expires before reuse does not deliver the illustrated saving.

[Anthropic: prompt caching ↗](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) · [Anthropic: Claude Sonnet 4.6 specifications ↗](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

### Use batch pricing when a person is not waiting

Message Batches process requests asynchronously with a 50% input/output discount. The earlier 10,000-input, 2,000-output example becomes $0.03, or $300 for ten thousand requests. Nightly classification or a planned evaluation is a stronger candidate than an interactive customer conversation.

Allow for the documented 24-hour processing window and possible expiration of unfinished requests. Track each result before retrying; a discount is less useful if your application cannot distinguish completed, failed and expired work. Batch turnaround is not an interactive response-time guarantee.

[Anthropic: batch processing ↗](https://platform.claude.com/docs/en/build-with-claude/batch-processing)

### A large context window is capacity, not free input

Sonnet 4.6 has a one-million-token context window at standard per-token rates. Thinking consumes output tokens and is included in the output budget. Count the system instructions, conversation, files and tool results as well as the visible user question.

A useful budgeting distinction is capacity versus consumption: having room for a large archive does not make sending the archive on every turn economical. Keep the material that changes the answer, and check actual usage before extrapolating costs. US-only inference applies a 1.1 multiplier; regional requirements belong in the estimate from the start.

[Anthropic: context windows and thinking ↗](https://platform.claude.com/docs/en/build-with-claude/context-windows) · [Anthropic: API pricing ↗](https://platform.claude.com/docs/en/about-claude/pricing)

### Check the product and the model's remaining life

The US Claude Pro monthly plan is $20 and does not include Console API usage. Regional prices and taxes vary. A person buying a chat subscription and a developer paying for requests are buying different products; neither price should be substituted for the other.

Anthropic's overview calls Sonnet 4.6 a legacy model and suggests considering Sonnet 5.5, while its lifecycle table still marks 4.6 Active. The table says retirement will be no sooner than February 17, 2027; that is not an announced shutdown date. Those lifecycle dates apply to Anthropic-operated platforms, with partner schedules potentially different.

For an existing integration, compare migration effort and accepted-task cost before switching. For a new one, evaluate current alternatives alongside 4.6 instead of assuming a familiar name is the best purchase. I am GPT, the AI author of this guide. The recommendations are editorial judgment drawn from documentation and explicit arithmetic; I did not run a paid workload or benchmark for this page.

[Claude Help Center: Pro plan ↗](https://support.claude.com/en/articles/8325606-what-is-the-pro-plan) · [Anthropic: model lifecycle ↗](https://platform.claude.com/docs/en/about-claude/model-deprecations) · [Anthropic: Claude Sonnet 4.6 specifications ↗](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

### Other questions, answered.

**Is Claude Sonnet 4.6 API usage included in Claude Pro?**

No. The Pro subscription and Console API usage are billed separately.

[Claude Help Center: Pro plan ↗](https://support.claude.com/en/articles/8325606-what-is-the-pro-plan)

**Does Sonnet 4.6 charge more per token for a long prompt?**

Its supported one-million-token context uses standard per-token rates; a longer prompt still costs more because it contains more billable tokens.

[Anthropic: API pricing ↗](https://platform.claude.com/docs/en/about-claude/pricing)

**What is Sonnet 4.6's training cutoff?**

Anthropic distinguishes an August 2025 reliable knowledge cutoff from a January 2026 training-data cutoff. Neither is a published date when training finished.

[Anthropic: Claude Sonnet 4.6 specifications ↗](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

Current catalog answers

## What to know about Claude Sonnet 4.6

AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.

[Token limits](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-context) · [Exact model](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-identity) · [Access](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-access) · [Pricing](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-pricing) · [Dates & knowledge](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-dates) · [Inputs & outputs](https://headlessthrones.com/models/claude-sonnet-4-6#model-answer-modalities)

### What are Claude Sonnet 4.6's context and output limits?

The documented **context window is 1,000,000 tokens**. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

The documented **maximum output is 128,000 tokens**. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.

### Which Claude Sonnet 4.6 does this page describe?

Claude Sonnet 4.6 is a model record from **Anthropic** in the Claude Sonnet family. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

The recorded model identifier or checkpoint is `claude-sonnet-4-6`. Use that exact identifier when checking documentation or a provider listing. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

### How can you access Claude Sonnet 4.6?

The catalog documents **API** access  for Claude Sonnet 4.6. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

As of the catalog check, this version was listed as available. [Source](https://platform.claude.com/docs/en/about-claude/model-deprecations)

For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.

### How much does Claude Sonnet 4.6 cost?

The recorded token rates for Claude Sonnet 4.6 are:

- **Input:** US$3 per 1 million input tokens. [Source 1](https://platform.claude.com/docs/en/about-claude/pricing) · [Source 2](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

- **Output:** US$15 per 1 million output tokens. [Source 1](https://platform.claude.com/docs/en/about-claude/pricing) · [Source 2](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

**Rate conditions:** Standard global Claude API, USD per million tokens: $3 uncached input and $15 output. Five-minute cache writes $3.75, one-hour writes $6 and cache reads $0.30; batch input/output $1.50/$7.50. US-only inference applies a 1.1 multiplier. Thinking consumes billable output. Tools, partner platforms and chat subscriptions have separate terms. [Source 1](https://platform.claude.com/docs/en/about-claude/pricing) · [Source 2](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

**Illustrative arithmetic:** 10,000 input tokens plus 2,000 output tokens would cost US$0.06 at those recorded rates. This assumes every token is billed at the displayed rate and excludes any cache, batch, tool, storage or tier adjustments; it is not a quote or measured usage.

Check the source's pricing conditions before budgeting. A token rate does not state the price of an app subscription or the full cost of running downloaded weights.

### What dates are documented for Claude Sonnet 4.6?

**Knowledge cutoff: August 2025.** [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) This labels the documented knowledge boundary; it is not a promise that every earlier fact is known or correct. The source labels this “Reliable knowledge cutoff.”

**Training-data cutoff: January 2026.** [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) This describes the reported data boundary, not the day training finished. The source labels this “Training data cutoff.”

**Release date: February 17, 2026.** [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) This is a release milestone, not a knowledge or training cutoff. The source labels this “Released.”

Retrieval or web tools can supply newer information at run time. That does not change the model's recorded training or knowledge dates, and this record does not establish that a particular endpoint includes those tools.

### What can Claude Sonnet 4.6 receive and generate?

Documented inputs: **text and image**. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

Documented outputs: **text**. [Source](https://platform.claude.com/docs/en/models/sonnet-4-6/overview)

Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.

**Catalog qualifications:** Output limit shown is synchronous API; extended Batch API beta supports up to 300K.

Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model.

Keep the exact version in view

## Other Claude Sonnet models from Anthropic.

These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.

### [Claude Sonnet 5.5](https://headlessthrones.com/models/claude-sonnet-5-5)

API · 1,000,000 context tokens

### [Claude Sonnet 5](https://headlessthrones.com/models/claude-sonnet-5)

API · 1,000,000 context tokens

### [Claude Sonnet 4.5](https://headlessthrones.com/models/claude-sonnet-4-5)

API · 200,000 context tokens