This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Anthropic has launched a newer release, Claude Opus 4.6. We suggest considering it instead.
Claude Opus 4.5 (Reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Claude Opus 4.5 (Reasoning) for your use-case.
Fastest
Anthropic
Amazon
Google Vertex
AzureOutput speed
Total 4 providers
Lowest Latency
AmazonGoogle VertexAnthropicAzureTime to first answer token
Total 4 providers
Lowest Price
Google VertexAnthropicAmazonAzureBlended price (per 1M tokens)
Total 4 providers
Claude Opus 4.5 is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Anthropic (48.4 t/s), Amazon (47.2 t/s), and Google Vertex (46.6 t/s).
- For latency, Amazon (6.01s), Google Vertex (7.22s), and Anthropic (7.56s) offer the lowest time to first answer token.
- For pricing, Google Vertex (3.85), Anthropic (3.85), and Amazon (3.85) offer the lowest blended prices per 1M tokens.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Claude Opus 4.5 (Reasoning)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
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
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Claude Opus 4.5 (Reasoning) providers
Claude Opus 4.5 (Reasoning) is available through 4 API providers: Google Vertex, Anthropic, Amazon, and Azure. Each provider offers different performance characteristics and pricing.
Claude Opus 4.5 (Reasoning) is currently available through 4 API providers that we benchmark and track.
The fastest providers for Claude Opus 4.5 (Reasoning) by output speed are Anthropic (48.4 t/s), Amazon (47.2 t/s), and Google Vertex (46.6 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for Claude Opus 4.5 (Reasoning) are Amazon (6.01s), Google Vertex (7.22s), and Anthropic (7.56s). Lower latency means faster initial response time.
The most affordable providers for Claude Opus 4.5 (Reasoning) by blended price are Google Vertex ($3.85 per 1M tokens), Anthropic ($3.85 per 1M tokens), and Amazon ($3.85 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Claude Opus 4.5 (Reasoning) are Google Vertex ($5.00 per 1M input tokens), Anthropic ($5.00 per 1M input tokens), and Amazon ($5.00 per 1M input tokens).
The providers with the lowest output token pricing for Claude Opus 4.5 (Reasoning) are Google Vertex ($25.00 per 1M output tokens), Anthropic ($25.00 per 1M output tokens), and Amazon ($25.00 per 1M output tokens).
2 of 4 providers support JSON mode for Claude Opus 4.5 (Reasoning): Google Vertex and Anthropic.
All 4 providers of Claude Opus 4.5 (Reasoning) support function calling (tool use).
The best provider for Claude Opus 4.5 (Reasoning) depends on your priorities: Anthropic offers the highest output speed, Amazon has the lowest latency, and Google Vertex provides the most competitive pricing.
When choosing a provider for Claude Opus 4.5 (Reasoning), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
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.
For information about Claude Opus 4.5 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview