Anthropic: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Anthropic for your use-case.
Most Intelligent
Claude Opus 5.5 (max with fallback)Claude Opus 5.5 (xhigh with fallback)Claude Sonnet 5.5 (max with fallback)Claude Opus 5.5 (high with fallback)Claude Fable 5.1 (xhigh with fallback)Intelligence Index
Total 46 models
Fastest
Claude Haiku 5.5 (max)Claude Haiku 5.5 (xhigh)Claude Haiku 5.5 (high)Claude Haiku 5.5 (medium)Claude Haiku 5.5 (low)Output speed
Total 46 models
Lowest Price
Claude Haiku 5.5 (max)Claude Haiku 5.5 (xhigh)Claude Haiku 5.5 (high)Claude Haiku 5.5 (medium)Claude Haiku 5.5 (low)Blended price (per 1M tokens)
Total 46 models
Anthropic offers 46 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Anthropic are Claude Opus 5.5 (max with fallback) (58), Claude Opus 5.5 (xhigh with fallback) (57), and Claude Sonnet 5.5 (max with fallback) (54).
- For output speed, the fastest models are Claude Haiku 5.5 (max) (234 t/s), Claude Haiku 5.5 (xhigh) (191 t/s), and Claude Haiku 5.5 (high) (176 t/s).
- For latency, Claude 4.5 Haiku (non-reasoning) (0.52s), Claude Sonnet 5 (non-reasoning) (0.81s), and Claude Opus 4.7 (non-reasoning, high) (0.86s) offer the lowest time to first answer token.
- For pricing, Claude Haiku 5.5 (max) ($0.08), Claude Haiku 5.5 (xhigh) ($0.08), and Claude Haiku 5.5 (high) ($0.08) offer the lowest blended prices per 1M tokens.
- For context window size, Claude Opus 5.5 (max with fallback) (1M), Claude Opus 5.5 (xhigh with fallback) (1M), and Claude Sonnet 5.5 (max with fallback) (1M) support the largest context windows on Anthropic.
- Claude Haiku 5.5 (max) offers both the fastest output and best pricing, making it attractive for throughput-sensitive and cost-conscious applications. Claude Opus 5.5 (max with fallback) leads in intelligence for tasks that require the highest quality.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5.5 (max with fallback) | 1M | Proprietary | 58 | $10.04 | 98 | 663.66 | 668.74 | -- | |||
Claude Opus 5.5 (xhigh with fallback) | 1M | Proprietary | 57 | $6.05 | 85 | 131.00 | 136.85 | -- | |||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 54 | $10.02 | 138 | 448.12 | 451.73 | -- | |||
Claude Opus 5.5 (high with fallback) | 1M | Proprietary | 52 | $3.46 | 84 | 35.05 | 41.00 | -- | |||
Claude Fable 5.1 (xhigh with fallback) | 1M | Proprietary | 50 | $10.89 | 66 | 83.03 | 90.56 | -- | |||
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Proprietary | 50 | $4.09 | 118 | 27.94 | 32.18 | -- | |||
Claude Fable 5.1 (max with fallback) | 1M | Proprietary | 49 | $13.04 | 66 | 128.91 | 136.49 | -- | |||
Claude Opus 5.5 (medium with fallback) | 1M | Proprietary | 48 | $2.45 | 83 | 15.35 | 21.35 | -- | |||
Claude Fable 5.1 (high with fallback) | 1M | Proprietary | 47 | $7.56 | 62 | 13.78 | 21.80 | -- | |||
Claude Fable 5.1 (medium with fallback) | 1M | Proprietary | 43 | $5.58 | 65 | 4.41 | 12.10 | -- | |||
Claude Sonnet 5.5 (high with fallback) | 1M | Proprietary | 41 | $1.64 | 119 | 12.35 | 16.56 | -- | |||
Claude Fable 5.1 (low with fallback) | 1M | Proprietary | 38 | $4.49 | 62 | 1.84 | 9.87 | -- | |||
Claude Haiku 5.5 (max) | 1M | Proprietary | 36 | $0.41 | 241 | 343.38 | 345.46 | -- | |||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 35 | $0.98 | 86 | 5.24 | 11.04 | -- | |||
Claude Haiku 5.5 (xhigh) | 1M | Proprietary | 34 | $0.25 | 196 | 53.58 | 56.14 | -- | |||
Claude Sonnet 5.5 (medium with fallback) | 1M | Proprietary | 30 | $0.78 | 114 | 2.88 | 7.27 | -- | |||
Claude Haiku 5.5 (high) | 1M | Proprietary | 30 | $0.16 | 191 | 17.88 | 20.50 | -- | |||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 25 | $0.51 | 116 | 1.34 | 5.65 | -- | |||
Claude Haiku 5.5 (medium) | 1M | Proprietary | 25 | $0.09 | 181 | 10.13 | 12.90 | -- | |||
Claude Haiku 5.5 (low) | 1M | Proprietary | 19 | $0.04 | 186 | 8.11 | 10.80 | -- | |||
Claude Opus 5 (xhigh) | 1M | Proprietary | -- | -- | 57 | 21.41 | 30.22 | -- | |||
Claude Sonnet 5 (low) | 1M | Proprietary | -- | -- | 71 | 1.24 | 8.28 | -- | |||
Claude Opus 5 (low) | 1M | Proprietary | -- | -- | 55 | 1.89 | 10.91 | -- | |||
Claude Sonnet 5 (max) | 1M | Proprietary | -- | -- | 86 | 97.62 | 103.45 | -- | |||
Claude Opus 4.5 | 200k | Proprietary | -- | -- | 63 | 17.67 | 25.60 | -- | |||
Claude Sonnet 4.6 (non-reasoning, high) | 1M | Proprietary | -- | -- | 50 | 0.98 | 11.04 | -- | |||
Claude Opus 4.7 (non-reasoning, high) | 1M | Proprietary | -- | -- | 54 | 0.75 | 10.01 | -- | |||
Claude Opus 4.5 (non-reasoning) | 200k | Proprietary | -- | -- | 57 | 1.06 | 9.76 | -- | |||
Claude Opus 4.6 (non-reasoning, high) | 1M | Proprietary | -- | -- | 46 | 2.01 | 12.77 | -- | |||
Claude 4 Opus (non-reasoning) | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
Claude Opus 4.6 (max) | 1M | Proprietary | -- | -- | 53 | 24.32 | 33.73 | -- | |||
Claude Opus 5 (high) | 1M | Proprietary | -- | -- | 55 | 14.72 | 23.74 | -- | |||
Claude 3 Opus | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
Claude 4 Opus | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
Claude 4.5 Sonnet | 1M | Proprietary | -- | -- | 55 | 14.93 | 24.02 | -- | |||
Claude 4.5 Sonnet (non-reasoning) | 1M | Proprietary | -- | -- | 49 | 1.08 | 11.35 | -- | |||
Claude Opus 4.8 (max) | 1M | Proprietary | -- | -- | 68 | 37.43 | 44.80 | -- | |||
Claude Sonnet 5 (xhigh) | 1M | Proprietary | -- | -- | 76 | 18.09 | 24.64 | -- | |||
Claude 4.5 Haiku | 200k | Proprietary | -- | -- | 101 | 18.36 | 23.30 | -- | |||
Claude Opus 5 (max) | 1M | Proprietary | -- | -- | 58 | 56.36 | 64.95 | -- | |||
Claude Sonnet 5 (high) | 1M | Proprietary | -- | -- | 72 | 4.42 | 11.38 | -- | |||
Claude 4.5 Haiku (non-reasoning) | 200k | Proprietary | -- | -- | 86 | 0.47 | 6.26 | -- | |||
Claude 4.1 Opus | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
Claude Fable 5 (with fallback) | 1M | Proprietary | -- | -- | 70 | 76.07 | 83.19 | -- | |||
Claude Sonnet 5 (non-reasoning) | 1M | Proprietary | -- | -- | 71 | 0.89 | 7.91 | -- | |||
Claude Sonnet 4.6 (max) | 1M | Proprietary | -- | -- | 65 | 92.39 | 100.12 | -- | |||
Claude Opus 4.7 (max) | 1M | Proprietary | -- | -- | 60 | 21.47 | 29.86 | -- | |||
Claude Sonnet 5 (medium) | 1M | Proprietary | -- | -- | 70 | 2.08 | 9.20 | -- | |||
Claude Sonnet 4.6 (non-reasoning, low) | 1M | Proprietary | -- | -- | 51 | 1.14 | 10.90 | -- | |||
Claude 4.1 Opus (non-reasoning) | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
Claude Opus 5 (medium) | 1M | Proprietary | -- | -- | 55 | 3.34 | 12.48 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Anthropic
Anthropic offers 46 models that we track: Claude Opus 5.5 (max with fallback), Claude Opus 5.5 (xhigh with fallback), Claude Sonnet 5.5 (max with fallback), Claude Opus 5.5 (high with fallback), Claude Fable 5.1 (xhigh with fallback), Claude Sonnet 5.5 (xhigh with fallback), Claude Fable 5.1 (max with fallback), Claude Opus 5.5 (medium with fallback), Claude Fable 5.1 (high with fallback), Claude Fable 5.1 (medium with fallback), Claude Sonnet 5.5 (high with fallback), Claude Fable 5.1 (low with fallback), Claude Haiku 5.5 (max), Claude Opus 5.5 (low with fallback), Claude Haiku 5.5 (xhigh), Claude Sonnet 5.5 (medium with fallback), Claude Haiku 5.5 (high), Claude Sonnet 5.5 (low with fallback), Claude Haiku 5.5 (medium), Claude Haiku 5.5 (low), Claude Opus 5 (xhigh), Claude Sonnet 5 (low), Claude Opus 5 (low), Claude Sonnet 5 (max), Claude Opus 4.5, Claude Sonnet 4.6 (non-reasoning, high), Claude Opus 4.7 (non-reasoning, high), Claude Opus 4.5 (non-reasoning), Claude Opus 4.6 (non-reasoning, high), Claude Opus 4.6 (max), Claude Opus 5 (high), Claude 4.5 Sonnet, Claude 4.5 Sonnet (non-reasoning), Claude Opus 4.8 (max), Claude Sonnet 5 (xhigh), Claude 4.5 Haiku, Claude Opus 5 (max), Claude Sonnet 5 (high), Claude 4.5 Haiku (non-reasoning), Claude Fable 5 (with fallback), Claude Sonnet 5 (non-reasoning), Claude Sonnet 4.6 (max), Claude Opus 4.7 (max), Claude Sonnet 5 (medium), Claude Sonnet 4.6 (non-reasoning, low), and Claude Opus 5 (medium).
The most intelligent model available on Anthropic is Claude Opus 5.5 (max with fallback) with an Intelligence Index score of 58.
The fastest model on Anthropic by output speed is Claude Haiku 5.5 (max) at 233.9 tokens per second.
The model with the lowest time to first answer token on Anthropic is Claude 4.5 Haiku (non-reasoning) at 0.52s. Lower latency means faster initial response time.
The most affordable model on Anthropic by blended price is Claude Haiku 5.5 (max) at $0.08 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Anthropic vary up to 100x across models, from $0.08 per 1M tokens for Claude Haiku 5.5 (max) to $7.70 per 1M tokens for Claude Fable 5 (with fallback).
Yes, Anthropic offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
9 of 46 models on Anthropic support JSON mode for structured output.
Yes, all 46 models on Anthropic support function calling (tool use).
Yes, Anthropic offers 38 reasoning models: Claude Opus 5.5 (max with fallback), Claude Opus 5.5 (xhigh with fallback), Claude Sonnet 5.5 (max with fallback), Claude Opus 5.5 (high with fallback), Claude Fable 5.1 (xhigh with fallback), Claude Sonnet 5.5 (xhigh with fallback), Claude Fable 5.1 (max with fallback), Claude Opus 5.5 (medium with fallback), Claude Fable 5.1 (high with fallback), Claude Fable 5.1 (medium with fallback), Claude Sonnet 5.5 (high with fallback), Claude Fable 5.1 (low with fallback), Claude Haiku 5.5 (max), Claude Opus 5.5 (low with fallback), Claude Haiku 5.5 (xhigh), Claude Sonnet 5.5 (medium with fallback), Claude Haiku 5.5 (high), Claude Sonnet 5.5 (low with fallback), Claude Haiku 5.5 (medium), Claude Haiku 5.5 (low), Claude Opus 5 (xhigh), Claude Sonnet 5 (low), Claude Opus 5 (low), Claude Sonnet 5 (max), Claude Opus 4.5, Claude Opus 4.6 (max), Claude Opus 5 (high), Claude 4.5 Sonnet, Claude Opus 4.8 (max), Claude Sonnet 5 (xhigh), Claude 4.5 Haiku, Claude Opus 5 (max), Claude Sonnet 5 (high), Claude Fable 5 (with fallback), Claude Sonnet 4.6 (max), Claude Opus 4.7 (max), Claude Sonnet 5 (medium), and Claude Opus 5 (medium). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Anthropic, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.