Claude Sonnet 5: the mid-tier model built for agentic coding
The canonical guide to claude-sonnet-5 - the default on Free and Pro plans when it shipped on 2026-06-30, and as of 2026-09-29 still Active and available on QCode today. 1M context, 128K output, and performance Anthropic describes as close to Opus 4.8, at roughly 40% lower price. Claude Sonnet 5.5, released 2026-09-28, is priced the same as Sonnet 5 ($2 / $10, cache reads $0.20).
Claude Sonnet 5 at a glance
Pinned dateless snapshot, released June 30, 2026. No -v1 suffix.
1M-token context (default and max) with 128K max output (up to 300K via a batches beta header).
$2 input / $10 output per MTok, confirmed as the standard rate on 2026-08-10.
Mid-tier model that Anthropic says is close to Opus 4.8, slotted between Haiku 4.5 and Opus 4.8.
At a glance: full specification
The verified facts for claude-sonnet-5 in one table, straight from Anthropic's model documentation.
| Specification | Claude Sonnet 5 |
|---|---|
| Model ID | claude-sonnet-5 (Bedrock: anthropic.claude-sonnet-5; OpenRouter: anthropic/claude-sonnet-5-20260630) |
| Release date | June 30, 2026 |
| Context window | 1,000,000 tokens (both default and maximum - no smaller variant) |
| Max output | 128K tokens (up to 300K with the output-300k-2026-03-24 Message Batches beta header) |
| Standard rate ($2/$10, confirmed 2026-08-10) | $2 / MTok input, $10 / MTok output; cache read $0.20 |
| Planned Sep 1 increase (cancelled) | Would have been $3 / MTok input, $15 / MTok output; cache read $0.30. Not in effect. |
| Thinking & effort | Adaptive thinking ON by default; effort low / medium / high / xhigh / max (default high). Manual thinking or non-default temperature/top_p/top_k return HTTP 400. |
| Knowledge cutoff | January 2026 |
| Availability | Free & Pro default at launch (2026-06-30); after Sonnet 5.5 shipped on 2026-09-28, Claude Code 2.1.284 made Sonnet 5.5 its default Sonnet. claude-sonnet-5 is still Active in Anthropic's deprecation table (retirement not sooner than 2027-06-30) and is available on QCode today; Max/Team/Enterprise; Claude Code; Claude API; Amazon Bedrock; Google Cloud Vertex AI; Microsoft Foundry; GitHub Copilot; OpenRouter |
Where Sonnet 5 shines - and where Opus 4.8 still leads
Anthropic frames Sonnet 5 as the best combination of speed and intelligence. It approaches Opus 4.8 without replacing it - here is an honest split.
Where Sonnet 5 shines
-
High-volume agentic coding
Fast tool loops, refactors and multi-file edits where you want strong quality at a lower per-token cost than Opus.
-
Speed-sensitive interactive work
Chat, pair-programming and IDE assist where low latency matters as much as raw depth of reasoning.
-
Long-context tasks on a budget
The full 1M-token window is available by default, so large repos and documents fit without paying Opus rates.
-
Default everyday driver
As the Free and Pro default at its June 2026 launch, it handles the majority of general and coding requests well.
Where Opus 4.8 still leads
-
The hardest coding tasks
Deep, ambiguous, long-horizon engineering problems still favour Opus 4.8's extra headroom.
-
High-stakes judgment
Nuanced reasoning, tricky trade-offs and careful review benefit from Opus 4.8's top-tier depth.
-
Cybersecurity & adversarial work
Opus 4.8 remains ahead on the most demanding security and red-team style reasoning.
-
Absolute peak quality
When you need the best answer regardless of price: as of 2026-09-29 Anthropic's newest Opus is Opus 5.5 (claude-opus-5-5, released 2026-09-22, available on QCode today); that rung was Opus 4.8 at Sonnet 5's launch.
Anthropic's positioning at the 2026-06-30 launch was qualitative - performance close to Opus 4.8 at roughly 40% lower price; Sonnet 5 approaches Opus 4.8, it does not match or beat it. Successor note (as of 2026-09-29): Claude Sonnet 5.5, released 2026-09-28, is priced the same as Sonnet 5 ($2 / $10, cache reads $0.20). The newest Opus from Anthropic is Claude Opus 5.5 (released 2026-09-22, $4 / $20, cache reads $0.20 - the official price list puts them at 0.05x the base input price). As of 2026-09-29, available on QCode today: claude-sonnet-5 and claude-opus-5-5.
Pricing summary
$2/$10 is the standard rate as of 2026-08-10. The $3/$15 increase once scheduled for 2026-09-01 was cancelled.
Current standard rate
$2 per million input tokens and $10 per million output tokens. Cache read $0.20. As of 2026-08-10 this is the long-term standard, not a limited promotion.
Planned rate (not applied)
$3 per million input and $15 per million output was scheduled for 2026-09-01 and will not happen. Do not budget post-August work at $3/$15.
Prompt caching
Cache read $0.20 (10% of the $2 input rate). A 5-minute cache write is 1.25x base input; a 1-hour cache write is 2x base input.
Sonnet 5 uses a new tokenizer: the same text consumes about 30% more tokens than Sonnet 4.6. So $2/$10 is best described as roughly cost-neutral versus Sonnet 4.6's $3/$15 on identical text - not a 33% discount. Compare on real request cost, not sticker price alone.
Which Claude model for which workload
A simple routing framework across the current Claude line-up. Match the model to the job rather than defaulting to the biggest one.
Fastest & cheapest
Reach for Haiku 4.5 on high-volume, latency-critical, low-complexity tasks: classification, extraction, routing and simple edits.
Best speed + intelligence
On QCode, Sonnet 5 remains the default workhorse for most agentic coding and general work as of 2026-09-29 (Anthropic's newest Sonnet is Sonnet 5.5, released 2026-09-28 at the same price as Sonnet 5) - strong quality, fast, close to Opus at ~40% lower price.
Peak reasoning
When you need a higher tier for the hardest coding, high-stakes judgment and cybersecurity: Opus 4.8 in this card was the flagship at Sonnet 5's launch; as of 2026-09-29, escalate to Opus 5.5 (claude-opus-5-5, released 2026-09-22, $4 / $20, available on QCode today).
Specialist flagship
Fable 5 ($10/$50, 1M context, 128K output) targets its own specialist workloads - use it when its particular strengths fit.
How to use Sonnet 5 on QCode
QCode gives you claude-sonnet-5 through a single API with no separate Anthropic account to manage.
Point to claude-sonnet-5
Set model to claude-sonnet-5 in any Anthropic-compatible request. The dateless snapshot means no date suffix to track.
Adaptive thinking by default
Thinking is on automatically at effort=high. Tune with effort low / medium / high / xhigh / max - don't send a manual thinking block.
Use it in Claude Code
Select Sonnet 5 as your Claude Code model for fast agentic loops, then escalate to claude-opus-5-5 only for the hardest steps (released 2026-09-22, $4 / $20, available on QCode today).
Skip unsupported params
Omit temperature, top_p and top_k - non-default values return HTTP 400, the same rule as Opus 4.7+.
client.messages.create(
model="claude-sonnet-5",
max_tokens=8000,
messages=[{"role": "user", "content": "Refactor this module"}]
# adaptive thinking is ON by default (effort="high")
# do NOT pass thinking={"type":"enabled"} or temperature -> HTTP 400
)
Migrating from Sonnet 4.6
claude-sonnet-5-5 has been available on QCode since 2026-09-29, so the recommended target here is chosen by workload between it and Sonnet 5 (Anthropic's deprecation table marks Sonnet 5 Active, retirement not sooner than 2027-06-30) - no forced migration, no deadline.
Sonnet 4.6 is NOT retired
claude-sonnet-4-6 status is Active, with a tentative retirement no sooner than February 17, 2027. You can keep using it; Sonnet 5 is simply the recommended successor whenever you choose to move.
1. Swap the model id
Change claude-sonnet-4-6 to claude-sonnet-5, then re-check output token budgets - the new tokenizer emits ~30% more tokens for the same text.
2. Drop legacy params
Remove any manual thinking block and non-default temperature/top_p/top_k. Rely on adaptive thinking and the effort parameter instead.
Frequently asked questions
Is Claude Sonnet 5 available on the free plan?
Yes. Claude Sonnet 5 became the default model on the Free and Pro plans at its 2026-06-30 launch, and Anthropic lists it for Max, Team and Enterprise plans, in Claude Code, the Claude API, Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry, GitHub Copilot and OpenRouter. It is still Active in Anthropic's deprecation table (retirement not sooner than 2027-06-30). As of 2026-09-29 Claude Code's own default Sonnet has been Sonnet 5.5 (released 2026-09-28, as of client 2.1.284), claude-sonnet-5-5 has been available on QCode since 2026-09-29, and claude-sonnet-5 remains available too.
How much does Claude Sonnet 5 cost per token?
The current standard rate is $2 per million input tokens and $10 per million output tokens. That figure began as introductory pricing; on 2026-08-10 Anthropic made it the permanent standard, and the $3/$15 step-up once scheduled for 2026-09-01 will not occur. Cache read is $0.20 (10% of input); a 5-minute cache write is 1.25x base input, a 1-hour write is 2x.
Did Claude Sonnet 5 introductory pricing end on August 31, 2026?
No. On 2026-08-10 Anthropic confirmed $2/$10 as the standard rate. The increase to $3/$15 planned for 2026-09-01 will not happen. Budget ongoing work at $2/$10.
What is the Claude Sonnet 5 context window?
Claude Sonnet 5 has a 1,000,000 (1M) token context window. That figure is both the default and the maximum; there is no smaller-context variant to opt into.
What is the maximum output for Claude Sonnet 5?
Maximum output is 128K tokens, and up to 300K tokens when you send the Message Batches beta header output-300k-2026-03-24.
Is Claude Sonnet 5 better than Opus 4.8?
No. At launch Anthropic positioned Sonnet 5 as a mid-tier model whose performance is close to Opus 4.8 at roughly 40% lower price, with Opus 4.8 leading on the hardest coding, judgment and cybersecurity tasks. Sonnet 5 approaches Opus 4.8; it does not match or beat it. As of 2026-09-29 the newest Opus from Anthropic is Claude Opus 5.5 (released 2026-09-22, $4 / $20, cache reads $0.20), available on QCode today as claude-opus-5-5; current Opus status: /claude-opus-5-2-status-tracker.
What is the Claude Sonnet 5 model id?
The model id is claude-sonnet-5, a pinned dateless snapshot with no -v1 suffix. On Amazon Bedrock it is anthropic.claude-sonnet-5, and on OpenRouter the slug is anthropic/claude-sonnet-5-20260630.
Can I use Claude Sonnet 5 in Claude Code?
Yes. Claude Sonnet 5 is available in Claude Code as well as the Claude API and every major cloud platform. Adaptive thinking is on by default with effort levels low, medium, high, xhigh and max (default high); manual extended thinking and non-default temperature/top_p/top_k return HTTP 400, so omit them.
Start building with Claude Sonnet 5 on QCode
Get claude-sonnet-5 and claude-opus-5-5 plus the full Claude line-up - Haiku 4.5, Opus 4.8 and Fable 5 - through one simple API.
Related guides
Claude Sonnet 5 pricing
Current $2/$10, the cancelled $3/$15 step-up, cache costs and the tokenizer caveat.
Sonnet 5 vs Opus 4.8
An honest, hedged comparison of where each model wins and how to route between them.
Sonnet 5 vs Sonnet 4.6
What changed, the new tokenizer, and why 4.6 stays Active until at least February 2027.
Sonnet 5 availability
Every plan and platform where claude-sonnet-5 is available, from Free to Bedrock and Vertex.
Sonnet 5 API guide
Model id, adaptive thinking, effort levels and the parameters that return HTTP 400.