Amux
All models

Anthropic: Claude Sonnet 5.5

Active

Anthropic: Claude Sonnet 5.5 is Anthropic’s upgraded Sonnet-class model that delivers greater performance than Claude Sonnet 5 while running more than 30% faster and at a lower cost for many workloads. Designed for agent-based coding, tool usage, and everyday professional tasks, it's ideal for developers and teams building fast and powerful AI agents.

Input:
Output:
Context length:
1M
Max output:
128K
Published:
2026-09-28
toolsreasoningstructuredOutputstreamingvisioncaching

Providers

Same model, different providers. Automatic routing picks the cheapest healthy one within the same quality tier.

Provider
amazon-bedrock—$2/1M tokens$10/1M tokens
Read$0.2/1M tokensWrite 5m$2.5/1M tokensWrite 1h$4/1M tokens
1M——
30% offanthropic—$2$1.4/1M tokens$10$7/1M tokens
Read$0.2$0.14/1M tokensWrite 5m$2.5$1.75/1M tokensWrite 1h$4$2.8/1M tokens
1M——
70% offLowestamux-special0.00%$2$0.6/1M tokens$10$3/1M tokens
Read$0.2$0.06/1M tokensWrite 5m$2.5$0.75/1M tokensWrite 1h$4$1.2/1M tokens
1M2.4s216.9 tps

Availability

7 days

Success rate of the requests Amux actually sent to each provider. Client errors are excluded from the denominator — a malformed request isn't the provider's fault.

Throughput

7 days

Average output speed on streaming requests, in tokens per second (TPS).

Latency

7 days

Average time to first token (TTFT) on streaming requests — how long from sending a request to receiving its first token.

Activity

7 days

Token usage and cost for this model over time, split by the provider that served each request.

Related models

More models from Anthropic

Anthropic: Claude Opus 5.51M contextfrom $0.4 / M tokens4 providersClaude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up. The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.
Anthropic: Claude Fable 5.11M contextfrom $3 / M tokens3 providersClaude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.
Anthropic: Claude Opus 51M contextfrom $0.5 / M tokens4 providersClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.