Claude Sonnet 5
The successor to Sonnet 4.6, approaching Opus 4.8 on reasoning, tool use and coding, with adaptive thinking that adjusts reasoning depth per task.
- Context
- 1M tokens
- Max output
- 128K
- Cutoff
- Released
Hosted API price
List price via Anthropic · per 1M tokens
- Input
- $2.00 /1M
- Output
- $10.00 /1M
- Hosted by
-
3 providers
Hosted API pricing
How we price
Order
Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.
Prices
Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.
Cost
Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.
Transparency and funding
- Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Every provider serving Claude Sonnet 5, cheapest input first. Set your monthly volume to see what each would bill.
| Provider | Input /1M | Output /1M | Cached input /1M | Cost at 10M in + 2M out | Link |
|---|---|---|---|---|---|
|
|
$2.00 | $10.00 | $0.20 | $40.00 | Visit website |
|
|
$2.00 | $10.00 | $0.20 | $40.00 | Visit website |
|
|
$2.00 | $10.00 | $40.00 | Visit website |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest Claude Sonnet 5 by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs Claude Sonnet 5 |
|---|---|---|---|---|---|---|
|
|
$2.7083 | $1.25 | $10.00 | 400K | Sep 2024 | −19% |
|
|
$2.7083 | $1.25 | $10.00 | 400K | Sep 2024 | −19% |
|
|
$2.75 | $1.50 | $9.00 | 1M | −17% | |
|
|
$3.00 | $2.00 | $8.00 | 1M | Jun 2024 | −10% |
|
|
$3.00 | $2.00 | $8.00 | 200K | Jun 2024 | −10% |
|
|
$3.3333 | $2.00 | $10.00 | 1M | Jan 2026 | |
|
|
$3.3333 | $2.00 | $10.00 | 1M | Feb 2026 | 0% |
|
|
$3.6667 | $2.00 | $12.00 | 1M | Jan 2025 | +10% |
|
|
$3.6667 | $2.00 | $12.00 | 1M | Feb 2026 | +10% |
|
|
$3.6667 | $2.00 | $12.00 | 1M | +10% | |
|
|
$3.75 | $2.50 | $10.00 | 256K | +13% |
USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Capabilities
What Claude Sonnet 5 accepts and can do, as published by Anthropic.
- Text Accepts and generates natural-language text.
- Image Accepts images as input alongside text.
- Reasoning Thinks before it answers, always on or as a switchable mode.
- Function calling Connect to external tools, APIs, and systems.
- Structured output Return responses in structured formats like JSON.
- Web search Search the web for up-to-date information.
- Code execution Write and execute code in a sandboxed environment.
- File upload Process uploaded documents, spreadsheets, and other files.
- MCP Connect to services via Model Context Protocol.
Common questions
What is Claude Sonnet 5 good for?
Reasoning, tool use and coding, with thinking depth adjusted per task. It takes text and images, at the lower-cost end of Anthropic's lineup, one tier above Haiku 4.5.
When is Claude Sonnet 5 not a good fit?
Audio or video input, or output other than text. Closed weights, so no self-hosting, and Opus 5 knows more recent events.
What is the cheapest way to run Claude Sonnet 5?
The cheapest hosted rate is $2.00 / $10.00 per 1M tokens via Anthropic.
How does Claude Sonnet 5 compare with Claude Sonnet 4.6?
Anthropic says Claude Sonnet 5 is a substantial step up from Claude Sonnet 4.6 in reasoning, tool use, coding and knowledge work, finishing tasks where earlier Sonnets stopped short and checking its own output unasked. It uses a new tokenizer and hallucinates less. Same 1M-token context and text and image input. Claude Sonnet 5 lists at 33% less per 1M input tokens and 33% less per 1M output tokens than Claude Sonnet 4.6. It came out 4 months later and has a newer knowledge cutoff (January 2026 against August 2025).
Can I self-host Claude Sonnet 5?
No. Anthropic does not publish the weights; Claude Sonnet 5 is available only through hosted APIs.
More from Anthropic
-
Claude Sonnet 4.6
1M context · cutoff Aug 2025
From $3.00 / $15.00 /1M in / out at the cheapest provider -
Claude Sonnet 4
200K context · cutoff Mar 2025
From $3.00 / $15.00 /1M in / out at the cheapest provider -
Claude Sonnet 4.5
200K context · cutoff Jan 2025
From $3.00 / $15.00 /1M in / out at the cheapest provider -
Claude Haiku 4.5
200K context · cutoff Feb 2025
From $1.00 / $5.00 /1M in / out at the cheapest provider -
Claude Opus 5
1M context · cutoff May 2026
From $5.00 / $25.00 /1M in / out at the cheapest provider -
Claude Opus 4.7
1M context · cutoff Jan 2026
From $5.00 / $25.00 /1M in / out at the cheapest provider -
Claude Opus 4.8
1M context · cutoff Jan 2026
From $5.00 / $25.00 /1M in / out at the cheapest provider -
Claude Opus 4.6
1M context · cutoff May 2025
From $5.00 / $25.00 /1M in / out at the cheapest provider