Model Comparison Analysis of API providers for GLM-5.2 (max) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Makora (FP8), Wafer, Fireworks, FriendliAI, Novita (FP8), GMI (FP8), Databricks, Parasail (FP8), CoreWeave, Baseten, Nebius (FP8), DeepInfra (FP8), Together AI, SiliconFlow (FP8).
Fastest
Output speed
Total 14 providers
Lowest Latency
Time to first answer token
Total 14 providers
Lowest Price
Blended price (per 1M tokens) Total 14 providers
GLM-5.2 (max) is available through 14 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 Fireworks (261.5 t/s), Baseten (239.5 t/s), Databricks (208.1 t/s).
- For latency, Fireworks (9.81s), Baseten (9.86s), Databricks (11.22s) offer the lowest time to first token.
- For pricing, GMI (FP8) (0.72), Wafer (0.79), DeepInfra (FP8) (0.80) offer the lowest blended prices per 1M tokens.
- Fireworks offers the best performance with both the highest speed and lowest latency. For cost optimization, GMI (FP8) provides the most competitive 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: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Speed vs. Price
Speed #
Measured by Output Speed (tokens per second)
### Output Speed: GLM-5.2 (max) Providers
### Latency vs. Output Speed: GLM-5.2 (max) Providers
Latency #
Measured by Time (seconds) to First Token
### Time to First Answer Token: GLM-5.2 (max) 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-5.2 (max) Providers
API Features #
### Function (Tool) Calling & JSON Mode: GLM-5.2 (max) Providers
### Context Window: GLM-5.2 (max) Providers
Summary Table of Key Comparison Metrics #
Frequently Asked Questions #
Common questions about GLM-5.2 (max) providers GLM-5.2 (max) is available through 14 API providers: Makora (FP8), Wafer, Fireworks, FriendliAI, Novita (FP8), GMI (FP8), Databricks, Parasail (FP8), CoreWeave, Baseten, Nebius (FP8), DeepInfra (FP8), Together AI, and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.
GLM-5.2 (max) is currently available through 14 API providers that we benchmark and track.
The fastest providers for GLM-5.2 (max) by output speed are Fireworks (261.5 t/s), Baseten (239.5 t/s), and Databricks (208.1 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 (max) are Together AI (0.82s), DeepInfra (FP8) (0.83s), and FriendliAI (0.90s). Lower latency means faster initial response time.
The most affordable providers for GLM-5.2 (max) by blended price are GMI (FP8) ($0.72 per 1M tokens), Wafer ($0.79 per 1M tokens), and DeepInfra (FP8) ($0.80 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 (max) are GMI (FP8) ($1.12 per 1M input tokens), Wafer ($1.20 per 1M input tokens), and DeepInfra (FP8) ($1.20 per 1M input tokens).
The providers with the lowest output token pricing for GLM-5.2 (max) are GMI (FP8) ($3.52 per 1M output tokens), Makora (FP8) ($3.99 per 1M output tokens), and Wafer ($4.10 per 1M output tokens).
Prices for GLM-5.2 (max) vary up to 2.4x across providers. The most affordable is GMI (FP8) at $0.72 per 1M tokens, while Nebius (FP8) charges $1.70 per 1M tokens.
Output speed for GLM-5.2 (max) varies significantly across providers. Fireworks is the fastest at 261.5 t/s, which is 5.4x faster than SiliconFlow (FP8) at 48.7 t/s.
13 of 14 providers support JSON mode for GLM-5.2 (max): Makora (FP8), Wafer, Fireworks, FriendliAI, Novita (FP8), GMI (FP8), Databricks, Parasail (FP8), CoreWeave, Baseten, Nebius (FP8), DeepInfra (FP8), and Together AI.
All 14 providers of GLM-5.2 (max) support function calling (tool use). The best provider for GLM-5.2 (max) depends on your priorities: Fireworks offers the highest output speed, Together AI has the lowest latency, and GMI (FP8) provides the most competitive pricing.
When choosing a provider for GLM-5.2 (max), 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 (max)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview