Back to models
Anthropic logo

Anthropic

Claude Sonnet 4.6

Anthropic’s balanced Claude tier for broad production use, coding, and agent orchestration.

Overall score
92
balancedcodingagents
Context window
200K tokens
Speed
Balanced
Input pricing
$3 / 1M input tokens
Output pricing
$15 / 1M output tokens

Score breakdown

Capability93
Use-case fit95
Cost efficiency85
Speed87
Reliability93
Agent readiness95
Ecosystem92

Scores combine benchmark signals, product experience, and editorial weighting. Use them as a practical guide, not an absolute truth claim.

Best for

CodingAgent automation

Works with

Claude CodeAnthropic APILangChainMCP clients

Modalities

textimagefile

Sources & trust

Officially verified core fields
Official linkSummaryDescriptionModalitiesContext windowMax outputTool supportPricingPricing page

Editorial fields such as shortlist guidance, strengths, caveats, and scoring remain clearly separated from official provider data.

Last verified: Apr 9, 2026

Strengths

  • One of the strongest default choices for practical coding and agent work.
  • Better price-performance than the premium Opus tier for many teams.

Things to watch

  • Still premium-priced versus budget routing tiers.
  • May not justify use on simple high-volume automation.

Best for