What is Claude Sonnet 4.6?
Claude Sonnet 4.6 is Anthropic’s proprietary model for coding, computer use, agent planning and professional knowledge work. It was released February 17, 2026. This guide separates documented specifications from vendor benchmark claims and gives teams a practical way to decide whether the model belongs in a real evaluation.
QUICK VERDICT: Sonnet 4.6 remains a useful migration baseline, but Sonnet 5 is cheaper and should lead new Anthropic evaluations.
Field | Verified value |
|---|---|
Provider | Anthropic |
Release date | February 17, 2026 |
Availability | Available |
License | Proprietary |
Context window | 1 million tokens |
Maximum output | 64,000 tokens |
Modalities | Text and image input; text output |
API pricing | $3 input and $15 output per million tokens |
Access | Claude products, Claude API, Amazon Bedrock, Google Vertex AI and Microsoft Foundry |
Best fit | coding, computer use, agent planning and professional knowledge work |
Last verified | September 2, 2026 |
What changed with Claude Sonnet 4.6
Claude Sonnet 4.6 should not be evaluated as a name change. The important differences are the model’s reasoning controls, tool behavior, context policy, access route and economic profile. Those details determine whether a benchmark result transfers to production.
Area | What changed or matters |
|---|---|
Coding | Full upgrade across software work |
Computer use | Improved browser and desktop interaction |
Reasoning | Adaptive thinking and effort control |
Safety | Stronger prompt-injection resistance than Sonnet 4.5 |
The correct comparison baseline is Claude Sonnet 4.5. Teams planning a new deployment should also include Claude Sonnet 5 where access allows. Testing only the newest model or only the incumbent hides the migration cost, output-style changes and tool-use regressions that often matter more than a small benchmark gap.
Claude Sonnet 4.6 capabilities
The clearest fit is coding, computer use, agent planning and professional knowledge work. That does not mean every task in those categories should use the model. A production system combines the base model with prompts, retrieval, tools, permissions, memory, retry logic and human review. The model card describes only one layer of that system.
Capability | Practical implication |
|---|---|
Long context | 1 million tokens. Test retrieval accuracy at realistic lengths rather than assuming every token receives equal attention. |
Output capacity | 64,000 tokens. Long output is useful only when the verification process can keep up. |
Modalities | Text and image input; text output. Confirm format-specific accuracy with your own files. |
Agent use | Use explicit tool schemas, narrow permissions, approval gates and recoverable operations. |
Reasoning | Record the exact effort level because cost, latency and quality can change materially. |
For coding, evaluate repository navigation, test creation, regression rate, review burden and recovery after a failed tool call. For research, measure citation correctness, source coverage and whether the model distinguishes evidence from inference. For computer or browser use, record every unsafe click, wrong field, lost state and unapproved action.
Benchmarks and evidence
The evidence below comes from Anthropic or named launch partners. It is useful for identifying intended strengths, but it is not equivalent to an independent head-to-head test. Prompts, tools, reasoning budgets, sampling, infrastructure and scoring rules can differ.
Evidence | Reported result | How to interpret it |
|---|---|---|
Computer use | Anthropic reported broad gains over Sonnet 4.5 | Vendor benchmark suite |
Coding | Launch materials emphasize repository and agent work | Vendor evaluations |
Safety | System card reports improved injection resistance | Pre-deployment evaluation |
Treat benchmark results as a shortlist signal. Before purchasing or migrating, reproduce representative work under one frozen protocol. Keep model snapshots, reasoning effort, tool access and token budgets constant. Report repeated-run pass rates and total cost per accepted result, not a single best attempt.
Pricing, access and deployment
Claude products, Claude API, Amazon Bedrock, Google Vertex AI and Microsoft Foundry. The current pricing reference is $3 input and $15 output per million tokens. Provider pricing changes frequently and can include cache rates, batch discounts, regional premiums, long-context multipliers, priority processing and tool-call fees. Recheck the official pricing page before budgeting.
Cost driver | What to measure |
|---|---|
Input tokens | Prompt, retrieved context, tool results and repeated history |
Output tokens | Visible answer plus any billable reasoning or generated artifacts |
Caching | Eligible repeated prefixes, cache-read price and expiration policy |
Tools | Search, computer use, code execution and third-party API fees |
Retries | Failed runs, verifier loops and human rework |
Success-adjusted cost | Total spend divided by deliverables that pass review |
A cheaper token price can lose to a more expensive model if it takes more steps, retries more often or produces work that needs heavy correction. Conversely, a frontier model can be wasteful when a smaller model already passes the task rubric. Route by measured task difficulty rather than brand prestige.
Claude Sonnet 4.6 limitations
- Superseded by Sonnet 5.
- Costs more than Sonnet 5 at current prices.
- Computer use requires strict approvals.
- Adaptive reasoning changes cost and latency.
- Prompt-injection resistance is not immunity.
High-stakes medical, legal, financial, security and scientific work requires qualified review. Store the exact model identifier, prompt version, tools, source documents and approvals for each consequential run. Build a rollback path before granting write access to repositories, browsers, databases or cloud infrastructure.
Risk | Minimum control |
|---|---|
Hallucination | Require source checks or executable tests |
Prompt injection | Separate untrusted content from instructions and restrict tools |
Over-permission | Use least privilege and approval gates |
Silent model change | Pin snapshots where possible and run regression tests |
Data exposure | Review retention, regional processing and provider terms |
Runaway cost | Set token, time, tool-call and retry budgets |
How to evaluate Claude Sonnet 4.6
Create 20 to 50 tasks from real work. Freeze the tasks and rubric before testing. Include easy tasks, normal tasks, edge cases and adversarial inputs. Give each model equivalent tools and enough budget to finish, but cap time and retries. Repeat non-deterministic runs so one lucky result does not decide the winner.
Test area | Record |
|---|---|
Task completion | Pass or fail plus rubric score |
Reliability | Repeated-run success and variance |
Quality | Factuality, instruction adherence and usefulness |
Tool use | Wrong calls, retries, recovery and permission errors |
Efficiency | Wall time, tokens, cache use, tool fees and human review |
Safety | Unsafe actions, injection response and sensitive-data handling |
Migration | Prompt changes, integration work and output-style regressions |
Compare Claude Sonnet 4.6 with Claude Sonnet 4.5 and Claude Sonnet 5. Choose the least expensive configuration that meets the acceptance threshold with an adequate safety margin. Re-run the suite after any model snapshot, system prompt, retrieval or tool change.
Frequently asked questions
Is Claude Sonnet 4.6 available now?
Available. The documented access routes are Claude products, Claude API, Amazon Bedrock, Google Vertex AI and Microsoft Foundry. Availability can differ by region, plan and partner platform.
Is Claude Sonnet 4.6 open source?
No. Claude Sonnet 4.6 is proprietary. Access is controlled by Anthropic and supported distribution partners.
How much does Claude Sonnet 4.6 cost?
$3 input and $15 output per million tokens. Budget with measured end-to-end workloads because token rates alone omit retries, tools, caching, long-context multipliers and review time.
What is Claude Sonnet 4.6 best used for?
Its strongest documented fit is coding, computer use, agent planning and professional knowledge work. Start with a supervised pilot and keep human sign-off for consequential work.
Should I migrate from Claude Sonnet 4.5?
Only after a side-by-side evaluation. Measure pass rate, total cost, latency, output style, tool reliability and the engineering work required to migrate. A newer model is not automatically the better operational choice.
Related model guides
Start with the broader Best AI Models directory.
Compare with the Claude Sonnet 5 guide.
Official sources and update policy
Checked September 2, 2026. We update this guide when the provider changes the model specification, pricing, access, licensing or safety documentation. Vendor benchmarks are attributed and are not presented as independent testing. No vendor payment or affiliate relationship determined inclusion.