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 Results for other workloads are historical and no longer updated.
OpenAI has launched a newer model, GPT-4o (Mar). We suggest considering it instead.
For more information, see comparison of GPT-4o (Mar) to other models and API provider benchmarks for GPT-4o (Mar).
GPT-4o (Nov '24) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of GPT-4o (Nov '24) for your use-case.
Fastest
OpenAI
AzureOutput speed
Total 2 providers
Lowest Latency
OpenAIAzureTime to first token
Total 2 providers
Lowest Price
AzureOpenAIBlended price (per 1M tokens)
Total 2 providers
GPT-4o (Nov) 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 OpenAI (141.4 t/s) and Azure (133.0 t/s).
- For latency, OpenAI (1.01s) and Azure (2.40s) offer the lowest time to first token.
- For pricing, Azure (2.38) and OpenAI (2.55) offer the lowest blended prices per 1M tokens.
- OpenAI offers the best performance with both the highest speed and lowest latency. For cost optimization, Azure provides the most competitive pricing.
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: GPT-4o (Nov '24)
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-4o (Nov '24) providers
GPT-4o (Nov '24) is currently available through 2 API providers that we benchmark and track.
All 2 providers of GPT-4o (Nov '24) support JSON mode for structured output.
All 2 providers of GPT-4o (Nov '24) support function calling (tool use).
When choosing a provider for GPT-4o (Nov '24), 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-4o (Nov '24)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview