# Claude Sonnet 4.6 API pricing 

Anthropic model · context window 1,000,000 · max input 1,000,000 · max output 128,000 tokens · vision, reasoning. Data last changed 2026-10-08. 

[Atom feed](https://apicostcheck.com/models/claude-sonnet-4-6/feed.xml) · [JSON](https://apicostcheck.com/data/models/claude-sonnet-4-6.json)

Get notified in any feed reader. 

| | |
| --- | --- |
| Input | $3.00 / 1M tokens |
| Output | $15.00 / 1M tokens |
| Cached input | $0.30 / 1M tokens |
| Cache write | $3.75 / 1M tokens |
| Cache write (1-hour TTL) | $6.00 / 1M tokens |
| Batch input | $1.50 / 1M tokens |
| Batch output | $7.50 / 1M tokens |
| Batch cached input | $0.15 / 1M tokens |
| Batch cache write | $1.875 / 1M tokens |
| Minimum cacheable prompt | 1,024 tokens |

[Calculate my cost →](https://apicostcheck.com/calculator/?model=claude-sonnet-4-6) 

Billing rules for caching, Batch and long prompts: [Anthropic API cost guide](https://apicostcheck.com/claude-api-cost-calculator/). 

## Source and checks

| | |
| --- | --- |
| Data source | [LiteLLM price list](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) (MIT) |
| Official pricing | [platform.claude.com ↗](https://platform.claude.com/docs/en/about-claude/pricing) |
| Last synced | 2026-10-08 |
| Last price change | No price changes recorded since tracking began on 2026-10-08. |
| Cross-check | Matches models.dev |
| Official check | Verified against the [official page](https://platform.claude.com/docs/en/about-claude/pricing.md) on 2026-10-08 (automatic check) |
| Price region | Global |

| Field | This site | Official | Status |
| --- | --- | --- | --- |
| Input | $3.00 | $3.00 | ✓ official |
| Output | $15.00 | $15.00 | ✓ official |
| Cached input | $0.30 | $0.30 | ✓ official |
| Cache write | $3.75 | $3.75 | ✓ official |
| Cache write (1-hour TTL) | $6.00 | $6.00 | ✓ official |
| Batch input | $1.50 | $1.50 | ✓ official |
| Batch output | $7.50 | $7.50 | ✓ official |
| Batch cached input | $0.15 | — | – unchecked |
| Batch cache write | $1.875 | — | – unchecked |
| Context window | 1,000,000 | — | – unchecked |
| Max input | 1,000,000 | — | – unchecked |
| Max output | 128,000 | — | – unchecked |

✓ official = the official page's value is in use (other sources' values noted) · ✓ verified = other source equals the official page · ≠ mismatch = differs and is held for confirmation; both shown · … pending = the automatic check could not read the page · – unchecked = not listed on the official page or not checked yet 

## What it costs per month

| Scenario (per month) | Claude Sonnet 4.6 |
| --- | --- |
| Customer support chatbot 5,000 req/day · 1,200 in · 400 out · cache 60% | $1,155 |
| RAG over documents 2,000 req/day · 8,000 in · 600 out · cache 30% | $1,609 |
| Coding agent 1,500 req/day · 25,000 in · 2,000 out · cache 80% | $2,379 |
| Deep reasoning 800 req/day · 3,000 in · 6,000 out · cache 20% | $2,337 |
| Batch processing 50,000 req/day · 1,500 in · 150 out · batch | $5,062 |

Adjust the numbers in the [calculator](https://apicostcheck.com/calculator/). 

## Cheaper alternatives

Lowest monthly cost for the chatbot scenario among reasoning models: 

- [Qwen Turbo](https://apicostcheck.com/models/qwen-turbo/) — $16.68/mo
- [MiMo V2.6 Flash](https://apicostcheck.com/models/mimo-v2.6-flash/) — $27.18/mo
- [GPT-5 nano](https://apicostcheck.com/models/gpt-5-nano/) — $28.14/mo
- [Gemini 2.5 Flash Lite](https://apicostcheck.com/models/gemini-2.5-flash-lite/) — $32.28/mo
- [Qwen Flash](https://apicostcheck.com/models/qwen-flash/) — $33.00/mo 

## Comparisons

- [Compare Claude Sonnet 4.6 with any model →](https://apicostcheck.com/compare/?m=claude-sonnet-4-6) 

## Price history

No price changes recorded since tracking began on 2026-10-08.

---
Source: https://apicostcheck.com/models/claude-sonnet-4-6/ · prices in USD per 1M tokens, synced 2026-10-08 · Free to reuse with a link to https://apicostcheck.com (CC BY 4.0). Prices derived from LiteLLM's model price list, MIT License, (c) 2023 Berri AI.