Claude Sonnet 5 in Cursor: Pricing and Uses

Superseded by Claude Sonnet 5.5Anthropic's medium-tier model in Cursor at $2 per million input tokens and $10 per million output, with cache reads at $0.10; it keeps Claude Sonnet 5's input and output rates and succeeds it. Press Enter for the full definition.. Cursor now recommends Claude Sonnet 5.5, which keeps the same $2 input and $10 output per million tokens and cuts cache reads from $0.20 to $0.10. Cursor hides Sonnet 5 by default.

If you are choosing a model today, start with our Sonnet 5.5 page or the current model guide. This page is for comparing Sonnet 5 with its successor.

Sonnet 5 took over from Sonnet 4.6 and is now, in Cursor's words, Anthropic's previous Sonnet model. Cursor rates it medium for speed and cost and frontier for intelligence. It says Sonnet 5 closes most of the gap to Opus 5 on real coding work while staying far cheaper per token. That made it a practical default for tasks that need substantial reasoning but don't justify the most expensive Anthropic model.

Cursor highlights thinking mode, multi-step planning and debugging, and purposeful tool use. Read those as signals for choosing the model, not as advice to use thinking on every request. A small edit with a clear test may finish faster and more cheaply on ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. or another lower-cost model. Sonnet earns its place when a task has enough ambiguity or cross-file reasoning to use the extra depth.

Choose Sonnet 5 for everyday repository work that still needs frontier reasoning: planning a feature, tracing a multi-layer bug, reviewing an unfamiliar subsystem, or carrying a tool-driven change through tests. For peak quality on the hardest tasks, Cursor's Sonnet 5 page now points to Opus 5.5. The boundary is task difficulty and the cost of failure, so it can move from one task to the next.

Escalate on evidence. Start Sonnet on a representative task with explicit acceptance checks. Move to Opus when Sonnet repeatedly misses a dependency, can't hold the full constraint set, or produces a plan that fails before implementation begins. Stay on Sonnet when both models reach the same verified result, because Opus 5 lists $5 input and $25 output against Sonnet's $2 and $10.

Run the comparison in fresh sessions from the same repository state. Switching models inside one long thread changes the cache and leaves the second model reading the first model's attempted solution. A clean A/B task gives a fairer view of final diff quality, elapsed time, redirects and total usage.

Cursor lists a 200k context window and a 1M maximum. The larger ceiling can hold more repository material, tool results and conversation history, but filling it has costs. Loading an entire codebase can make the relevant file harder to pick out, and it spends tokens on context the task may never use. Start with the smallest useful working set, and expand only when evidence points outside it.

Long context carries no price step on Sonnet 5. Prompts above 200k tokens bill at the same base rates as shorter ones, and Cursor lists no long-context multiplier for this model. The extra tokens still cost money: a 600k prompt contains three times as many input tokens as a 200k prompt, before cache behavior is considered.

Sonnet 5 is a third-party model. The X SubscriptionThe subscription Cursor is sold through: one plan for Grok, Cursor and X, with Free, Plus, Premium, Super and Ultra tiers, per-seat Teams, a weekly included pool for Cursor models shared with Grok, and third-party models billed at API list price from prepaid credit. Press Enter for the full definition. charges it to prepaid credit at the rates below, and legacy plans draw on the Other ModelsOn legacy Cursor plans, the monthly pool for supported third-party models from providers such as Anthropic, Google and OpenAI, separate from Cursor Models. On The X Subscription third-party models are billed from prepaid credit instead. Press Enter for the full definition. pool, which starts at Pro and grows on the higher legacy plans. Cursor StartAn India-only legacy individual plan at ₹649 a month centered on Cursor's own models, with cloud and mobile access but without Other Models, Auto, Bugbot, Automations or the Agent SDK; Cursor names Plus as the comparable plan on The X Subscription. Press Enter for the full definition. covers only the Cursor ModelsOn legacy Cursor plans, the monthly usage pool for Cursor's own models (Grok 4.7, Grok 4.6, Grok 4.5 and Composer 2.5), kept separate from the third-party Other Models pool. The X Subscription replaces it with one weekly pool. Press Enter for the full definition. pool, so Sonnet 5 isn't available on it.

Output carries the highest published rate, so long explanations and large generated files can cost more than a short prompt suggests. Cache reads cost one tenth of fresh input, which rewards stable, repeated context. Changing models mid-session breaks the cache, so a workflow that hops between providers can cost more than the four rates in the table imply.

Teams and Enterprise accounts also pay the Cursor Token Rate on eligible requests, whether they select a third-party model directly or an eligible Auto modeCursor's automatic model router with Cost, Balance and Intelligence options that trade price against model capability. Press Enter for the full definition. routes to one. That rate sits on top of Sonnet's provider pricing. Check the live usage dashboard for the effective cost instead of multiplying only the model's input and output rows.

In Cursor, Sonnet 5 can search files and folders, search the web, read and edit files, run shell commands, control the browser, generate images, ask questions and fetch rules. What it can do in a given session still depends on the product surface, approval mode, sandbox, connected credentials and team policy. A tool listed on the model card doesn't grant an account or bypass a repository control.

A rollout started today should use Sonnet 5.5, which Cursor now recommends. The method below works the same for either model.

Pick two or three task classes and a fixed review sheet. Record whether the result passed, how often a person redirected the run, the elapsed time, token use, and which model would otherwise have handled the task. That evidence tells you whether Sonnet belongs as a default, an escalation tier, or an option for one team whose work benefits from its reasoning style.

Date the evaluation. Model behavior, Cursor's harness and provider rates can change while the model name stays the same in an old report. After a material release, a short rerun tells you more than one successful pilot treated as a permanent ranking.