Claude Sonnet 4.5 vs Claude Haiku 4.5
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Claude Sonnet 4.5 da Anthropic e Claude Haiku 4.5 da Anthropic são dois modelos de IA de destaque. O Claude Sonnet 4.5 oferece uma janela de contexto de 1M tokens a $3.00/$15.00 por milhão de tokens, enquanto o Claude Haiku 4.5 oferece 200K tokens de contexto a $1.00/$5.00 por milhão de tokens. Veja abaixo a comparação completa de benchmarks, latência e custos.
Troque e Compare Qualquer Modelo
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Claude Sonnet 4.5
Modelo Principal de FronteiraO Claude Sonnet 4.5 da Anthropic é um modelo de IA projetado para raciocínio corporativo de fronteira, programação avançada e cargas de produção, oferecendo janela de contexto de 1M, velocidade de 90 tokens/s, índice de inteligência de 91/1
$3.00 / 1M
$15.00 / 1M
1M tokens
77.8%
Claude Haiku 4.5
Inferência UltrarrápidaO Claude Haiku 4.5 da Anthropic é um modelo de IA projetado para respostas em tempo real com latência ultrabaixa e roteamento de alto volume, oferecendo janela de contexto de 200K, velocidade de 140 tokens/s, índice de inteligência de 54/10
$1.00 / 1M
$5.00 / 1M
200K tokens
58.2%
Principais Diferenças em Resumo
- Claude Haiku 4.5 is 3.0x cheaper for API usage (input + output tokens combined).
- Claude Sonnet 4.5 has a larger context window (1M vs 200K tokens).
- Claude Haiku 4.5 is faster at 140 tok/s vs 90 tok/s.
- Claude Sonnet 4.5 leads on SWE-bench coding (77.8% vs 58.2%).
| Feature | Claude Sonnet 4.5 | Claude Haiku 4.5 |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 91 | 54 |
Provider | Anthropic | Anthropic |
Input Price Cost per million input tokens | $3.00 / 1M | $1.00 / 1M |
Output Price Cost per million output tokens | $15.00 / 1M | $5.00 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $2.31 / 1M | $0.77 / 1M |
Context Window Maximum input + output tokens | 1M tokens~1,500 A4 pages of text | 200K tokens~300 A4 pages of text |
Max Output Tokens Per single request | 64K | 64K |
Throughput Speed Tokens generated per second | 90 tok/s | 140 tok/s |
SWE-bench Verified Real-world software engineering | 77.8% | 58.2% |
GPQA Diamond Graduate-level reasoning | 70.2% | 62.1% |
Cached Input Price Prompt caching discount per 1M tokens | $0.30 / 1M | $0.10 / 1M |
Quem vence em cada categoria?
At-a-glance decision frameworkPontuações de Benchmarks Verificadas
Official evaluation metrics verified by independent third-party research labs.
Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Extremely difficult, closed-ended questions spanning the frontier of human expert knowledge.
Autonomous multi-step tasks executed inside a real command-line terminal environment.
Research-grade coding problems drawn from real scientific and numerical workloads.
Contamination-free competitive programming problems collected continuously over time.
American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.
Accuracy when reasoning over very large inputs that fill the model context window.
Tokens emitted per second during active generation streaming.
Latência e Tempo de Resposta
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Simulador Interativo de Custo de Tokens
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Claude Sonnet 4.5 · Strengths & Key Advantages
- Janela de contexto de 1M com limite máximo de saída de 64K tokens (SWE-bench Verified 77.8% · GPQA Diamond 70.2%)
- Taxa de transferência rápida de 90 tokens/segundo com latência inicial (TTFT) de 900 ms
- Economia de API competitiva ($3/$15 por 1M de tokens) com suporte a cache de prompts e saídas JSON estruturadas
Considerations & Trade-offs
- Modelo proprietário em nuvem; não permite download dos pesos para execução local offline
- Para alto volume de requisições, recomenda-se ativar o cache de prompts e a Batch API para reduzir custos
Claude Haiku 4.5 · Strengths & Key Advantages
- Janela de contexto de 200K com limite máximo de saída de 64K tokens (SWE-bench Verified 58.2% · GPQA Diamond 62.1%)
- Taxa de transferência rápida de 140 tokens/segundo com latência inicial (TTFT) de 280 ms
- Economia de API competitiva ($1/$5 por 1M de tokens) com suporte a cache de prompts e saídas JSON estruturadas
Considerations & Trade-offs
- Modelo proprietário em nuvem; não permite download dos pesos para execução local offline
- Em derivações científicas extremas, modelos pesados dedicados exclusivamente ao raciocínio oferecem maior profundidade
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Claude Sonnet 4.5 | Claude Haiku 4.5 |
|---|---|---|
Cost per Task Estimated USD to finish one task | $2.10 | $0.70 |
Output Tokens / Task Tokens generated per task | 55K | 20K |
Reasoning Tokens / Task Thinking tokens burned per task | 30K | 10K |
Especificações Técnicas
Architecture, release timeline, capabilities, and modalities.
| Feature | Claude Sonnet 4.5 | Claude Haiku 4.5 |
|---|---|---|
| Official API Model ID (SDK) | claude-sonnet-4-5-20251101 | claude-haiku-4-5-20251001 |
| API Protocol | Anthropic Messages API + AWS Bedrock + Vertex AI | Anthropic Messages API + AWS Bedrock + Vertex AI |
| Release Date | 2025-11 | 2025-10 |
| Knowledge Cutoff | March 2025 | July 2025 |
| Architecture | Hybrid Reasoning | Lightweight High-Speed Multimodal Transformer |
| Parameters | Confidential | Confidential |
| Enterprise Rate Limits (RPM / TPM) | 4,000 – 10,000 RPM (Tier 4 + Priority Tier) · 4,000,000 – 10,000,000 TPM | 4,000 – 10,000 RPM (Tier 4 + Priority Tier) · 800,000 – 2,000,000 TPM |
| Long-Context Tier (>128K/200K) | Standard rate up to 200K tokens; 2x input/output tier above 200K tokens | Standard rate up to 200K tokens; 2x input/output tier above 200K tokens |
| Prompt Cache Policy & TTL | $0.3/1M cached read (90% off); 5-min default & 1-hour extended TTL | $0.1/1M cached read (90% off); 5-min default & 1-hour extended TTL |
| Computer Use / GUI Agent | Supported (Screen coordinate grounding, browser & desktop GUI action loops) | Supported (Screen coordinate grounding, browser & desktop GUI action loops) |
| MCP & Parallel Tool Calling | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Native Web Search Citations + Code Execution Tool + MCP Connectors | Native Web Search Citations + Code Execution Tool + MCP Connectors |
| Official Fine-Tuning Support | Custom Model Tuning via Amazon Bedrock & Prompt Distillation | Custom Model Tuning via Amazon Bedrock & Prompt Distillation |
| Multimodal Token Billing | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) |
| Quantization & Min GPU VRAM | Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API) | Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API) |
| Safety & Frontier Classification | Anthropic RSP ASL-2 / ASL-3 Constitutional Safety Evaluated | Anthropic RSP ASL-2 / ASL-3 Constitutional Safety Evaluated |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier | SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier |
| Input Modalities | text, vision | text, vision |
| Output Modalities | text | text |
Claude Sonnet 4.5 vs Claude Haiku 4.5: Respostas Rápidas (FAQ)
Which is more intelligent, Claude Sonnet 4.5 or Claude Haiku 4.5?
Claude Sonnet 4.5 is more intelligent. It scores 91 compared with 54 on the composite Intelligence Index.
Which model is faster?
Claude Haiku 4.5 is faster, generating 140 tokens per second compared with 90 tokens per second.
Which model is cheaper to run?
Claude Haiku 4.5 is cheaper at $0.77 per 1M tokens blended, compared with $2.31 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Claude Haiku 4.5 has lower latency, with a time to first token of 0.28s compared with 0.90s.
Which model has a larger context window?
Claude Sonnet 4.5 has a larger context window, supporting 1M tokens compared with 200K tokens.
Veredito
Tanto Claude Sonnet 4.5 (Indicado para raciocínio corporativo de fronteira, programação avançada e cargas de produção, arquiteturas RAG corporativas e integração escalável via API.) quanto Claude Haiku 4.5 (Indicado para respostas em tempo real com latência ultrabaixa e roteamento de alto volume, arquiteturas RAG corporativas e integração escalável via API.) entregam excelente desempenho: Claude Sonnet 4.5 lidera em inteligência geral e programação, Claude Haiku 4.5 oferece geração mais rápida e Claude Haiku 4.5 apresenta o melhor custo-benefício em produção.
Perguntas Frequentes (FAQ)
Qual é melhor para programação e raciocínio, Claude Sonnet 4.5 ou Claude Haiku 4.5?+
Nas avaliações de inteligência e código, Claude Sonnet 4.5 leva vantagem. Confira os gráficos SWE-bench e GPQA acima para detalhes.
Qual modelo tem a API mais barata, Claude Sonnet 4.5 ou Claude Haiku 4.5?+
O Claude Sonnet 4.5 custa $3.00 / $15.00 por 1M de tokens (entrada/saída) e o Claude Haiku 4.5 custa $1.00 / $5.00. No custo combinado, Claude Haiku 4.5 é mais econômico.
Qual modelo possui maior janela de contexto e velocidade?+
O Claude Sonnet 4.5 suporta 1M tokens de contexto contra 200K tokens do Claude Haiku 4.5, enquanto Claude Haiku 4.5 entrega maior velocidade de geração.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Claude Haiku 4.5 vs. GPT-5 Chat: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Gemini 3.1 Pro vs. Claude Sonnet 4.5: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- GPT-5 mini vs. Claude Haiku 4.5: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- GPT-5 nano vs. Claude Haiku 4.5: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Aion-Mini: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Gemini 3.6 Flash: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Fontes oficiais: Documentação oficial de API da Anthropic e Anthropic e benchmarks independentes (2026).