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 Results for other workloads are historical and no longer updated.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 model, Claude Sonnet 5 (Non-reasoning). We suggest considering it instead.

For more information, see comparison of Claude Sonnet 5 (Non-reasoning) to other models and API provider benchmarks for Claude Sonnet 5 (Non-reasoning).

Claude Sonnet 4.6 (Non-reasoning, High Effort) logo
Anthropic
•

Claude Sonnet 4.6

•

Proprietary model

•

Released February 2026

Claude Sonnet 4.6 (Non-reasoning, High Effort) API Provider Benchmarking & Analysis

Model Comparison

Analysis of API providers for Claude Sonnet 4.6 (Non-reasoning, High Effort) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Amazon Bedrock, Microsoft Azure, Google, and Anthropic.

Fastest

#1
AmazonAmazon
44.2 t/s
#2
AzureAzure
42.3 t/s
#3
GoogleGoogle
41.9 t/s
#4
AnthropicAnthropic
41.6 t/s

Output speed

Total 4 providers

Lowest Latency

#1
GoogleGoogle
1.17 s
#2
AnthropicAnthropic
1.22 s
#3
AmazonAmazon
1.33 s
#4
AzureAzure
1.51 s

Time to first token

Total 4 providers

Lowest Price

#1
AmazonAmazon
$2.31
#2
AzureAzure
$2.31
#3
GoogleGoogle
$2.31
#4
AnthropicAnthropic
$2.31

Blended price (per 1M tokens)

Total 4 providers

Claude Sonnet 4.6 (Non-reasoning) 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 Amazon (44.2 t/s), Azure (42.3 t/s), and Google (41.9 t/s).
  • For latency, Google (1.17s), Anthropic (1.22s), and Amazon (1.33s) offer the lowest time to first token.
  • For pricing, Amazon (2.31), Azure (2.31), and Google (2.31) offer the lowest blended prices per 1M tokens.
  • Amazon provides an excellent balance of speed and cost-effectiveness. For the lowest latency, Google is the best choice.

Highlights

Speed

Output tokens per second · Higher is better

End-to-End Response Time

Seconds · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Reduction in input token cost due to cache hit relative to input price. Formula: 1 - (Cache Hit Price per Token / Input Token Price), where cache hit price is the first-party cache hit price or the median provider cache hit price. Note that this discount figure does not account for all costs associated with cache hits, such as cache write and storage costs.

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Claude Sonnet 4.6 (Non-reasoning, High Effort)

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant
Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency

Measured by Time (seconds) to First Token

Time to First Token

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

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

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features

Amazon Bedrock logoAmazon Bedrock
200k
Proprietary
--
45
1.50
12.70
--
Microsoft Azure logoMicrosoft Azure
200k
Proprietary
--
43
1.97
13.56
--
Google logoGoogle
200k
Proprietary
--
44
1.29
12.68
--
Anthropic logoAnthropic
1M
Proprietary
--
44
1.71
13.16
--

Frequently Asked Questions

Common questions about Claude Sonnet 4.6 (Non-reasoning, High Effort) providers

Claude Sonnet 4.6 (Non-reasoning, High Effort) is available through 4 API providers: Amazon, Azure, Google, and Anthropic. Each provider offers different performance characteristics and pricing.

Claude Sonnet 4.6 (Non-reasoning, High Effort) is currently available through 4 API providers that we benchmark and track.

The fastest providers for Claude Sonnet 4.6 (Non-reasoning, High Effort) by output speed are Amazon (44.2 t/s), Azure (42.3 t/s), and Google (41.9 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for Claude Sonnet 4.6 (Non-reasoning, High Effort) are Google (1.17s), Anthropic (1.22s), and Amazon (1.33s). Lower latency means faster initial response time.

The most affordable providers for Claude Sonnet 4.6 (Non-reasoning, High Effort) by blended price are Amazon ($2.31 per 1M tokens), Azure ($2.31 per 1M tokens), and Google ($2.31 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 Sonnet 4.6 (Non-reasoning, High Effort) are Amazon ($3.00 per 1M input tokens), Azure ($3.00 per 1M input tokens), and Google ($3.00 per 1M input tokens).

The providers with the lowest output token pricing for Claude Sonnet 4.6 (Non-reasoning, High Effort) are Amazon ($15.00 per 1M output tokens), Azure ($15.00 per 1M output tokens), and Google ($15.00 per 1M output tokens).

All 4 providers of Claude Sonnet 4.6 (Non-reasoning, High Effort) support function calling (tool use).

The best provider for Claude Sonnet 4.6 (Non-reasoning, High Effort) depends on your priorities: Amazon offers the highest output speed, Google has the lowest latency, and Amazon provides the most competitive pricing.

When choosing a provider for Claude Sonnet 4.6 (Non-reasoning, High Effort), 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 Sonnet 4.6 (Non-reasoning, High Effort)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview