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 Results for other workloads are historical and no longer updated.
Z AI has launched a newer model, GLM-4.7. We suggest considering it instead.
For more information, see comparison of GLM-4.7 to other models and API provider benchmarks for GLM-4.7.
GLM-4.6 (Reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of GLM-4.6 (Reasoning) for your use-case.
Fastest
Novita
DeepInfra (FP4)Output speed
Total 3 providers
Lowest Latency
NovitaDeepInfra (FP4)Time to first answer token
Total 3 providers
Lowest Price
DeepInfra (FP4)Novita
Together AIBlended price (per 1M tokens)
Total 3 providers
GLM-4.6 is available through 3 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 Novita (33.4 t/s) and DeepInfra (FP4) (21.1 t/s).
- For latency, Novita (63.89s) and DeepInfra (FP4) (96.03s) offer the lowest time to first answer token.
- For pricing, DeepInfra (FP4) (0.37), Novita (0.72), and Together AI (0.76) offer the lowest blended prices per 1M tokens.
- Novita offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra (FP4) 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: GLM-4.6 (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 GLM-4.6 (Reasoning) providers
GLM-4.6 (Reasoning) is available through 3 API providers: DeepInfra (FP4), Together AI, and Novita. Each provider offers different performance characteristics and pricing.
GLM-4.6 (Reasoning) is currently available through 3 API providers that we benchmark and track.
The fastest providers for GLM-4.6 (Reasoning) by output speed are Novita (33.4 t/s) and DeepInfra (FP4) (21.1 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 GLM-4.6 (Reasoning) are Novita (63.89s) and DeepInfra (FP4) (96.03s). Lower latency means faster initial response time.
The most affordable providers for GLM-4.6 (Reasoning) by blended price are DeepInfra (FP4) ($0.37 per 1M tokens), Novita ($0.72 per 1M tokens), and Together AI ($0.76 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 GLM-4.6 (Reasoning) are DeepInfra (FP4) ($0.50 per 1M input tokens), Novita ($0.55 per 1M input tokens), and Together AI ($0.60 per 1M input tokens).
The providers with the lowest output token pricing for GLM-4.6 (Reasoning) are DeepInfra (FP4) ($2.00 per 1M output tokens), Together AI ($2.20 per 1M output tokens), and Novita ($2.20 per 1M output tokens).
Prices for GLM-4.6 (Reasoning) vary up to 2.1x across providers. The most affordable is DeepInfra (FP4) at $0.37 per 1M tokens, while Together AI charges $0.76 per 1M tokens.
Output speed for GLM-4.6 (Reasoning) varies significantly across providers. Novita is the fastest at 33.4 t/s, which is 1.6x faster than DeepInfra (FP4) at 21.1 t/s.
2 of 3 providers support JSON mode for GLM-4.6 (Reasoning): DeepInfra (FP4) and Novita.
All 3 providers of GLM-4.6 (Reasoning) support function calling (tool use).
For GLM-4.6 (Reasoning), Novita offers the best performance with highest speed and lowest latency. For cost optimization, DeepInfra (FP4) provides the most competitive pricing.
When choosing a provider for GLM-4.6 (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-4.6 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview