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 Results for other workloads are historical and no longer updated.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 release, GLM-5.3. We suggest considering it instead.
GLM-5.2 (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of GLM-5.2 (Non-reasoning) for your use-case.
Fastest
Baseten (FAST)
Databricks
Nebius (FP4)
ScalewayBasetenOutput speed
Total 7 providers
Lowest Latency
Baseten (FAST)DatabricksNebius (FP4)Scaleway
SiliconFlow (FP8)Time to first token
Total 7 providers
Lowest Price
Bitdeer AIBasetenSiliconFlow (FP8)DatabricksBaseten (FAST)Blended price (per 1M tokens)
Total 7 providers
GLM-5.2 (Non-reasoning) is available through 7 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 Baseten (FAST) (338.2 t/s), Databricks (224.0 t/s), and Nebius (FP4) (220.2 t/s). Speed varies significantly across providers, with a 391% difference between the fastest and slowest.
- For latency, Baseten (FAST) (0.53s), Databricks (0.91s), and Nebius (FP4) (1.01s) offer the lowest time to first token.
- For pricing, Bitdeer AI (0.37), Baseten (0.82), and SiliconFlow (FP8) (0.85) offer the lowest blended prices per 1M tokens. Prices vary up to 6.8x across providers.
- Baseten (FAST) offers the best performance with both the highest speed and lowest latency. For cost optimization, Bitdeer AI 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-5.2 (Non-reasoning)
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 GLM-5.2 (Non-reasoning) providers
GLM-5.2 (Non-reasoning) is available through 7 API providers: Baseten (FAST), Nebius (FP4), Scaleway, Bitdeer AI, SiliconFlow (FP8), Baseten, and Databricks. Each provider offers different performance characteristics and pricing.
GLM-5.2 (Non-reasoning) is currently available through 7 API providers that we benchmark and track.
The fastest providers for GLM-5.2 (Non-reasoning) by output speed are Baseten (FAST) (338.2 t/s), Databricks (224.0 t/s), and Nebius (FP4) (220.2 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-5.2 (Non-reasoning) are Baseten (FAST) (0.53s), Databricks (0.91s), and Nebius (FP4) (1.01s). Lower latency means faster initial response time.
The most affordable providers for GLM-5.2 (Non-reasoning) by blended price are Bitdeer AI ($0.37 per 1M tokens), Baseten ($0.82 per 1M tokens), and SiliconFlow (FP8) ($0.85 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-5.2 (Non-reasoning) are Bitdeer AI ($0.60 per 1M input tokens), SiliconFlow (FP8) ($1.30 per 1M input tokens), and Nebius (FP4) ($1.40 per 1M input tokens).
The providers with the lowest output token pricing for GLM-5.2 (Non-reasoning) are Bitdeer AI ($1.88 per 1M output tokens), SiliconFlow (FP8) ($4.09 per 1M output tokens), and Nebius (FP4) ($4.40 per 1M output tokens).
Prices for GLM-5.2 (Non-reasoning) vary up to 6.8x across providers. The most affordable is Bitdeer AI at $0.37 per 1M tokens, while Scaleway charges $2.52 per 1M tokens.
Output speed for GLM-5.2 (Non-reasoning) varies significantly across providers. Baseten (FAST) is the fastest at 338.2 t/s, which is 4.9x faster than SiliconFlow (FP8) at 68.8 t/s.
6 of 7 providers support JSON mode for GLM-5.2 (Non-reasoning): Baseten (FAST), Nebius (FP4), Scaleway, Bitdeer AI, Baseten, and Databricks.
All 7 providers of GLM-5.2 (Non-reasoning) support function calling (tool use).
For GLM-5.2 (Non-reasoning), Baseten (FAST) offers the best performance with highest speed and lowest latency. For cost optimization, Bitdeer AI provides the most competitive pricing.
When choosing a provider for GLM-5.2 (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-5.2 (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview