Claude Sonnet 5 pricing
Anthropic ·
claude-sonnet-5 ·
1M context
· 61st cheapest of 89 current models
Estimate Claude Sonnet 5 for your workload Source and check date
Rates last checked against the vendor’s own published pricing on 2026-11-10.
What Claude Sonnet 5 costs
| Rate | Per 1M tokens | Per 1K tokens | What it covers |
|---|---|---|---|
| Input | $2 | $0.002 | Every token you send: prompt, history, documents. |
| Output | $10 | $0.01 | Every token the model generates, including hidden reasoning tokens. |
| Cached input | $0.2 | $0.0002 | Input served from the provider’s prompt cache. |
| Cache write (5 minutes) | $2.5 | $0.0025 | Charged once, to put a prefix into the cache for the default five minutes. Estimates use this rate. |
| Cache write (1 hour) | $4 | $0.004 | The same write with a one-hour lifetime, for prompts reused less often than every five minutes. |
What that means in practice
The same three workloads are costed on every model page, so these numbers are directly comparable across the catalog. No prompt caching and no batch discount is assumed — the figures are what you pay before you optimize anything.
Support chatbot
2,500 six-turn conversations a day
$8,055 / month
$0.107 per conversation · $96,660 a year
An 800-token system prompt, 400-token questions and 900-token answers, over six turns — each turn re-sending everything before it.
Document summarizer
1,000 single-shot summaries a day
$972 / month
$0.032 per conversation · $11,664 a year
One 12,000-token document in, an 800-token summary out, no conversation history. The case where input dominates the bill.
Coding agent
200 twelve-turn sessions a day
$5,616 / month
$0.936 per conversation · $67,392 a year
A 3,000-token system prompt, 1,500-token instructions and 2,500-token responses over twelve turns. Long sessions are where the quadratic cost of re-sent history stops being theoretical.
Change the assumptions in the calculator
Cheaper, and scored at least as capable
Every model below costs less on a blended rate and carries a capability score at least as high as Claude Sonnet 5’s. The score is a rough estimate, not a benchmark — treat it as a shortlist, not a verdict.
| Model | Input | Output | Blended saving | |
|---|---|---|---|---|
| GPT-6.1 Terra | $1 | $5 | 50% | |
| DeepSeek V4 Flash | $0.3 | $1.2 | 87% | |
| MiMo V2.6 Pro | $0.435 | $0.87 | 86% | |
| GLM-5.3 | $1.4 | $4.4 | 46% | |
| Qwen 3.8 Max | $2 | $6 | 25% |
Head to head
- Claude Sonnet 5 vs Gemini 3.1 Pro
- Claude Sonnet 5 vs Gemini 3.7 Flash
- Claude Sonnet 5 vs Gemini 4 Argon
- Claude Sonnet 5 vs GPT-5.4
- Claude Sonnet 5 vs GPT-5.5
- Claude Sonnet 5 vs GPT-6.1 Sol
Specification
| Context window | 1M tokens |
|---|---|
| Maximum output | 128K tokens |
| Provider | Anthropic |
| Status | Current |
| Reasoning model | Yes |
| Vision | Yes |
| Token counting | Estimated at ~3.6 characters per token (Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose) |
| Batch API | 50% off both rates for non-interactive work |
Price history
PromptSpend has recorded Claude Sonnet 5 since 2026-08-02. Tracking began on 2026-08-02, so anything the vendor did before then is not on record here.
| Date | Rate | Was | Now | What happened |
|---|---|---|---|---|
| 2026-08-16 | Input | $3 | $2 | The vendor changed the rate |
| 2026-08-16 | Output | $15 | $10 | The vendor changed the rate |
| 2026-08-16 | Cached input | $0.3 | $0.2 | The vendor changed the rate |
| 2026-08-16 | Cache write | $3.75 | $2.5 | The vendor changed the rate |
| 2026-08-22 | Input | $2 | $3 | The vendor changed the rate |
| 2026-08-22 | Output | $10 | $15 | The vendor changed the rate |
| 2026-08-22 | Cached input | $0.2 | $0.3 | The vendor changed the rate |
| 2026-08-22 | Cache write | $2.5 | $3.75 | The vendor changed the rate |
| 2026-09-01 | Input | $3 | $2 | The vendor changed the rate |
| 2026-09-01 | Output | $15 | $10 | The vendor changed the rate |
| 2026-09-01 | Cached input | $0.3 | $0.2 | The vendor changed the rate |
| 2026-09-01 | Cache write | $3.75 | $2.5 | The vendor changed the rate |
Every row, with the commit that published it, is in the price-history dataset; price news is also available as an Atom feed.
Where these numbers come from
Last checked against its source on 2026-11-10, and the published rates last actually moved on 2026-09-01. Source of record: the vendor’s own published pricing.
The vendor page a human checked
Regional and data-residency premiums, priority tiers, server-side tool fees and negotiated discounts are not included. Prices change without notice; this page is rebuilt every time the catalog does.
Common questions
How much does Claude Sonnet 5 cost?
Claude Sonnet 5 costs $2 per 1M input tokens and $10 per 1M output tokens at the standard tier, as last checked against the vendor’s own published pricing on 2026-11-10.
How much does Claude Sonnet 5 cost to run for a month?
On PromptSpend's three standard workloads, Claude Sonnet 5 costs about $8,055 for a support chatbot, $972 for a document summarizer and $5,616 for a coding agent each month. No prompt caching and no batch discount is assumed, and the same workloads are costed on every model page, so the figures compare directly.
Is there a cheaper alternative to Claude Sonnet 5?
Yes. GPT-6.1 Terra ($1 in, $5 out), DeepSeek V4 Flash ($0.3 in, $1.2 out) and MiMo V2.6 Pro ($0.435 in, $0.87 out) cost less on a blended rate and carry a capability score at least as high. The score is a rough estimate, not a benchmark, so treat the list as a shortlist.
How large is the context window of Claude Sonnet 5?
Claude Sonnet 5 accepts up to 1M tokens of context and can produce up to 128K tokens of output.
Has the price of Claude Sonnet 5 changed?
Yes. Since 2026-08-02, the vendor has changed its rates on 3 days (12 rates in all), most recently on 2026-09-01. PromptSpend began tracking prices on 2026-08-02, so earlier changes are not on record.
Where do the prices for Claude Sonnet 5 come from?
They come from the vendor’s own published pricing and were last checked on 2026-11-10. Regional and data-residency premiums, priority tiers, server-side tool fees and negotiated discounts are not included.