Claude Sonnet 4.6 logo

Claude Sonnet 4.6

Anthropic · Released Feb 2026

Conditional

Superseded by Claude Sonnet 5 (shipped Jun 30, 2026) as the default mid-tier workhorse. Sonnet 4.6's $3/$15 pricing and 1M-token context are now matched by a successor with a 13.4-point Terminal-Bench 2.1 jump at the same rate card. Choose 4.6 only for pinned deployments or where Sonnet 5's ~30% higher token count and removed temperature/top_p/top_k are disqualifying.

Is it right for you?

Good for

  • Pinned or reproducibility-sensitive deployments — teams that need a stable, unchanged model behind their pipeline rather than migrating to Sonnet 5
  • Balanced production coding and document analysis — strong speed/quality/cost tradeoff at $3/$15 with a 1M-token context window
  • Workloads where the Sonnet 5 tokenizer's ~30% higher token count would inflate cost, or that depend on temperature/top_p/top_k (removed in Sonnet 5)

Not good for

  • New default workloads — Sonnet 5 supersedes it with a 13.4-point Terminal-Bench 2.1 jump and near-Opus performance at the same rate card; start new work there
  • Longest-horizon agentic coding — Sonnet 5 finishes multi-step tasks 4.6 stalled on; Opus 4.8 / Fable 5 lead the frontier tier

How it performs by task

Code generation

Very Good

Strong for its generation; Sonnet 5 now finishes multi-step tasks 4.6 stalled on

Document analysis

Very Good

1M-token context handles large documents well; solid balance of quality and cost

Agentic coding

Good

Capable but superseded — Sonnet 5's 13.4-point Terminal-Bench 2.1 jump is the reason to migrate

Pricing

Input

$3 / 1M tokens

Output

$15 / 1M tokens

Context

1M tokens

View full pricing

Benchmarks

BenchmarkScoreSource
SWE-bench Verified72.7% Source
MMLU-Pro84.2% Source
HumanEval93.7% Source

Verdict history

Jul 15, 2026
copy edit to brevity standard — detail preserved in children

Verification log

  • Pricing— No changes

    Automated agent

  • Pricing— No changes

    Automated agent

  • Profile— Updated

    Automated agent

    Rewrote seed-junk entry in place (slug kept): name 'Claude 4 Sonnet' -> 'Claude Sonnet 4.6'; release 2026-03-15 -> real 2026-02-17; context set to 1M; pricing confirmed $3/$15; verdict recommended -> conditional (superseded by Sonnet 5, still available for pinned/reproducible use). Summary/strengths/audiences/task-ratings/sources fully replaced with sourced Sonnet 4.6 predecessor data.

  • Pricing— No changes

    Automated agent

  • Pricing— No changes

    Automated agent

    Pricing unchanged: $3/$15 per 1M tokens. Current Sonnet tier is 4.6 on the pricing page.

  • Pricing— No changes

    Automated agent

    Sonnet 4 pricing unchanged at $3/$15 in legacy section. Current Sonnet 4.6 also at $3/$15.

  • Pricing— No changes

    Automated agent

  • Profile— No changes

    Imported at launch

  • Pricing— No changes

    Imported at launch

How we evaluate