GLM-5.1 (Non-reasoning) API Provider Benchmarking & Analysis
Analysis of API providers for GLM-5.1 (Non-reasoning) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include FriendliAI, DeepInfra (FP8), Parasail, Novita (FP8), SiliconFlow (FP8).
Fastest
FriendliAI
SiliconFlow (FP8)
Novita (FP8)
Parasail
DeepInfra (FP8)Output speed
Total 5 providers
Lowest Latency
FriendliAIDeepInfra (FP8)ParasailNovita (FP8)SiliconFlow (FP8)Time to first answer token
Total 5 providers
Lowest Price
FriendliAIDeepInfra (FP8)ParasailNovita (FP8)SiliconFlow (FP8)Blended price (per 1M tokens)
Total 5 providers
GLM-5.1 is available through 5 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 FriendliAI (117.6 t/s), SiliconFlow (FP8) (50.1 t/s), Novita (FP8) (47.5 t/s). Speed varies significantly across providers, with a 341% difference between the fastest and slowest.
- For latency, FriendliAI (1.01s), DeepInfra (FP8) (1.23s), Parasail (1.75s) offer the lowest time to first token.
- For pricing, FriendliAI (2.15), DeepInfra (FP8) (2.15), Parasail (2.15) offer the lowest blended prices per 1M tokens.
- FriendliAI stands out as the overall leader, ranking first across all three categories: speed, latency, and pricing.
Highlights
Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above!
Pricing
Pricing: Input and Output Prices: GLM-5.1 Providers
Speed vs. Price: GLM-5.1 Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed: GLM-5.1 Providers
Latency vs. Output Speed: GLM-5.1 Providers
Latency
Measured by Time (seconds) to First Token
Time to First Token: GLM-5.1 Providers
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: GLM-5.1 Providers
API Features
DeepInfra (FP8)
SiliconFlow (FP8)Summary Table of Key Comparison Metrics
Frequently Asked Questions
Common questions about GLM-5.1 (Non-reasoning) providers
GLM-5.1 (Non-reasoning) is available through 5 API providers: FriendliAI, DeepInfra (FP8), Parasail, Novita (FP8), and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.
GLM-5.1 (Non-reasoning) is currently available through 5 API providers that we benchmark and track.
The fastest providers for GLM-5.1 (Non-reasoning) by output speed are FriendliAI (117.6 t/s), SiliconFlow (FP8) (50.1 t/s), and Novita (FP8) (47.5 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 GLM-5.1 (Non-reasoning) are FriendliAI (1.01s), DeepInfra (FP8) (1.23s), and Parasail (1.75s). Lower latency means faster initial response time.
The most affordable providers for GLM-5.1 (Non-reasoning) by blended price are FriendliAI ($2.15 per 1M tokens), DeepInfra (FP8) ($2.15 per 1M tokens), and Parasail ($2.15 per 1M tokens). Blended price uses a 3:1 input to output token ratio.
The providers with the lowest input token pricing for GLM-5.1 (Non-reasoning) are FriendliAI ($1.40 per 1M input tokens), DeepInfra (FP8) ($1.40 per 1M input tokens), and Parasail ($1.40 per 1M input tokens).
The providers with the lowest output token pricing for GLM-5.1 (Non-reasoning) are FriendliAI ($4.40 per 1M output tokens), DeepInfra (FP8) ($4.40 per 1M output tokens), and Parasail ($4.40 per 1M output tokens).
Output speed for GLM-5.1 (Non-reasoning) varies significantly across providers. FriendliAI is the fastest at 117.6 t/s, which is 4.4x faster than DeepInfra (FP8) at 26.7 t/s.
4 of 5 providers support JSON mode for GLM-5.1 (Non-reasoning): FriendliAI, DeepInfra (FP8), Parasail, and Novita (FP8).
All 5 providers of GLM-5.1 (Non-reasoning) support function calling (tool use).
FriendliAI leads across all key metrics for GLM-5.1 (Non-reasoning), offering the fastest speed, lowest latency, and most competitive pricing.
When choosing a provider for GLM-5.1 (Non-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 GLM-5.1 (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview