Claude Sonnet 5.5 Released: 30% Faster, 30% Cheaper [Sept 28]
Anthropic launched Claude Sonnet 5.5 on September 28, 2026 — the second model in the Claude 5.5 family, six days after Opus 5.5. Sonnet 5.5 runs 30% faster than Sonnet 5 and costs up to 30% less for most work. In agentic build benchmarks, Sonnet 5.5 produced apps scoring level with Opus 5 while taking only 3.6 iterations per build (Opus 5 averaged 7.7). Fewest failed tool calls of any Anthropic model tested.
The AI coding race is now about cost per completed task, not benchmark scores. Sonnet 5.5 makes routine agentic work dramatically cheaper. For most day-to-day Claude Code sessions — code review, refactors, writing tests, debugging — Sonnet 5.5 is now the correct default. Opus 5.5 stays for genuinely complex multi-hour work.
API model string: claude-sonnet-5-5. Drop-in replacement for claude-sonnet-5. Recommended for: standard coding tasks, tool use, moderate reasoning, cost-sensitive agentic workflows. For hardest tasks, use Opus 5.5 or Fable 5.1.
Top 5 Things to Know About Claude Sonnet 5.5
-
30% faster than Sonnet 5 — Latency drops meaningfully for interactive coding sessions.
-
Up to 30% cheaper — Anthropic’s efficiency push aimed at long agentic runs.
-
Matches Opus 5 on agentic builds — In Anthropic’s internal benchmarks, Sonnet 5.5 produced apps scoring level with Opus 5 in half the iterations (3.6 vs 7.7).
-
Fewest failed tool calls — Best tool use reliability of any Claude model tested to date. Matters for production agents.
-
Complement to Opus 5.5 — Anthropic positions the 5.5 family as a two-model system: Sonnet 5.5 for everyday, Opus 5.5 for complex.
When to Use Sonnet 5.5 vs Opus 5.5
| Task | Use |
|---|---|
| Standard coding, refactors, tests | Sonnet 5.5 |
| Multi-hour autonomous agent runs | Opus 5.5 |
| Complex reasoning + planning | Opus 5.5 |
| Tool-heavy production agents | Sonnet 5.5 (fewest failed calls) |
| Cost-sensitive at scale | Sonnet 5.5 |
| Hardest edge-case reasoning | Fable 5.1 |
FAQ
What is Claude Sonnet 5.5?
Claude Sonnet 5.5 is Anthropic’s balanced Claude model released September 28, 2026. It’s the second model in the Claude 5.5 family, following Opus 5.5. Sonnet 5.5 is 30% faster and up to 30% cheaper than Sonnet 5, while matching Opus 5 on agentic build benchmarks.
When was Claude Sonnet 5.5 released?
Claude Sonnet 5.5 was released on September 28, 2026 — six days after Claude Opus 5.5 launched on September 22.
Should I use Sonnet 5.5 or Opus 5.5?
Use Sonnet 5.5 for everyday coding, refactors, tool use, and cost-sensitive workflows. Use Opus 5.5 for genuinely complex multi-hour agentic runs, hardest reasoning tasks, and situations where task quality matters more than cost or speed.
What model string do I use for Claude Sonnet 5.5?
Use claude-sonnet-5-5 in API calls. Drop-in replacement for claude-sonnet-5 — same request schema, no code changes needed beyond the model string.
How does Sonnet 5.5 compare to Sonnet 4.5?
Claude Sonnet 4.5 reached end-of-life on September 29, 2026. Anthropic recommends migrating to Sonnet 5.5 (or Sonnet 4.6 for teams on the 4.x line). Sonnet 5.5 is dramatically more capable at agentic work.