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 Results for other workloads are historical and no longer updated.
GPT-4 Turbo API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of GPT-4 Turbo for your use-case.
Fastest
Azure
OpenAIOutput speed
Total 2 providers
Lowest Latency
AzureOpenAITime to first token
Total 2 providers
Lowest Price
AzureOpenAIBlended price (per 1M tokens)
Total 2 providers
GPT-4 Turbo is available through 2 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 Azure (121.6 t/s) and OpenAI (31.8 t/s).
- For latency, Azure (1.96s) and OpenAI (3.23s) offer the lowest time to first token.
- For pricing, Azure (12.00) and OpenAI (12.00) offer the lowest blended prices per 1M tokens.
- Azure stands out as the overall leader, ranking first across all three categories: speed, latency, and pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: GPT-4 Turbo
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First 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 GPT-4 Turbo providers
GPT-4 Turbo is currently available through 2 API providers that we benchmark and track.
All 2 providers of GPT-4 Turbo support JSON mode for structured output.
All 2 providers of GPT-4 Turbo support function calling (tool use).
Azure leads across all key metrics for GPT-4 Turbo, offering the fastest speed, lowest latency, and most competitive pricing.
When choosing a provider for GPT-4 Turbo, 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 GPT-4 Turbo's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview