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 Results for other workloads are historical and no longer updated.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-5.3 (max). We suggest considering it instead.

For more information, see comparison of GLM-5.3 (max) to other models and API provider benchmarks for GLM-5.3 (max).

Z AI

•

GLM-5.2

•

Open weights model

•

Released June 2026

GLM-5.2 (max) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of GLM-5.2 (max) for your use-case.

Fastest

Nebius (FP4)

267.2 t/s

Baseten (FAST)

266.1 t/s

Databricks

257.7 t/s

Fireworks

235.8 t/s

Modular

207.8 t/s

Output speed

Total 19 providers

Lowest Latency

Baseten (FAST)

8.16 s

Nebius (FP4)

8.50 s

Databricks

8.62 s

Fireworks

9.92 s

Modular

10.32 s

Time to first answer token

Total 19 providers

Lowest Price

Bitdeer AI

$0.37

DeepInfra (FP4)

$0.49

CoreWeave

$0.49

GMI (FP8)

$0.59

Fireworks

$0.82

Blended price (per 1M tokens)

Total 19 providers

GLM-5.2 (max) is available through 19 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 Nebius (FP4) (267.2 t/s), Baseten (FAST) (266.1 t/s), and Databricks (257.7 t/s). Speed varies significantly across providers, with a 302% difference between the fastest and slowest.
For latency, Baseten (FAST) (8.16s), Nebius (FP4) (8.50s), and Databricks (8.62s) offer the lowest time to first answer token.
For pricing, Bitdeer AI (0.37), DeepInfra (FP4) (0.49), and CoreWeave (0.49) offer the lowest blended prices per 1M tokens. Prices vary up to 6.8x across providers.

Highlights

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Endpoint Accuracy

Endpoint Accuracy Index: GLM-5.2 (max)

v1.0 · Composite of BFCL v4-500, HLE-250 and AA-LCR-25 run against each provider endpoint · Percentage of the reference endpoint, with 95% confidence interval · Higher is better

Composite measure of how much of a model's accuracy a given provider endpoint preserves, from re-running BFCL v4-500, HLE-250 and AA-LCR-25 against that endpoint. Where a self-hosted reference endpoint exists, scores are expressed as a percentage of that reference (100 = matches reference); lower scores indicate accuracy lost to quantisation, sampling defaults, or other endpoint-side configuration. Scores are point-in-time snapshots. Methodology.

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Reduction in input token cost due to cache hit relative to input price. Formula: 1 - (Cache Hit Price per Token / Input Token Price), where cache hit price is the first-party cache hit price or the median provider cache hit price. Note that this discount figure does not account for all costs associated with cache hits, such as cache write and storage costs.

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: GLM-5.2 (max)

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token: GLM-5.2 (max) Providers

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

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

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features



FriendliAI	100%	1M	Open	$0.87	153	0.85	17.16	13.06
Baseten	n/a	524k	Open	$1.04	263	0.65	10.16	7.60
Novita	98%	1.05M	Open	$0.88	72	1.74	36.35	27.68
Parasail	98%	1M	Open	--	187	1.14	14.51	10.69
CoreWeave	97%	262k	Open	$0.96	100	1.37	26.47	20.08
Multiverse Computing	n/a	1M	Open	$2.31	135	0.91	19.44	14.82
DeepInfra	73%	1.05M	Open	$0.65	60	1.32	43.18	33.49
Nebius	100%	432k	Open	$2.94	265	1.06	10.49	7.55
Together AI	97%	262k	Open	$1.05	113	0.74	22.80	17.65
Scaleway	75%	262k	Open	$4.37	127	1.35	21.09	15.79
Databricks	n/a	1M	Open	$0.87	229	0.88	11.82	8.75
Bitdeer AI	n/a	1M	Open	$0.33	75	3.48	36.82	26.67
Fireworks	100%	1M	Open	$0.64	229	1.41	12.35	8.75
GMI	n/a	1.05M	Open	--	--	--	--	--
Baseten	93%	1.05M	Open	$0.65	121	2.12	22.82	16.56
Modular	n/a	164k	Open	$0.88	217	0.71	12.25	9.24
Zai	n/a	1M	Open	$0.96	75	4.31	37.73	26.73
Mistral	n/a	1.05M	Open	$0.76	200	1.04	13.53	9.99
SiliconFlow	99%	1.05M	Open	$0.85	78	1.46	33.68	25.78

Frequently Asked Questions

Common questions about GLM-5.2 (max) providers

GLM-5.2 (max) is available through 19 API providers: FriendliAI, Baseten (FAST), Novita (FP8), Parasail (NVFP4), CoreWeave, Multiverse Computing, DeepInfra (FP4), Nebius (FP4), Together AI, Scaleway, Databricks, Bitdeer AI, Fireworks, GMI (FP8), Baseten, Modular, Zai, Mistral, and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.

GLM-5.2 (max) is currently available through 19 API providers that we benchmark and track.

The fastest providers for GLM-5.2 (max) by output speed are Nebius (FP4) (267.2 t/s), Baseten (FAST) (266.1 t/s), and Databricks (257.7 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-5.2 (max) are Baseten (FAST) (8.16s), Nebius (FP4) (8.50s), and Databricks (8.62s). Lower latency means faster initial response time.

The most affordable providers for GLM-5.2 (max) by blended price are Bitdeer AI ($0.37 per 1M tokens), DeepInfra (FP4) ($0.49 per 1M tokens), and CoreWeave ($0.49 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 Bitdeer AI ($0.60 per 1M input tokens), DeepInfra (FP4) ($0.75 per 1M input tokens), and CoreWeave ($0.76 per 1M input tokens).

The providers with the lowest output token pricing for GLM-5.2 (max) are Bitdeer AI ($1.88 per 1M output tokens), DeepInfra (FP4) ($2.40 per 1M output tokens), and CoreWeave ($2.42 per 1M output tokens).

Prices for GLM-5.2 (max) 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 (max) varies significantly across providers. Nebius (FP4) is the fastest at 267.2 t/s, which is 4.0x faster than DeepInfra (FP4) at 66.6 t/s.

18 of 19 providers support JSON mode for GLM-5.2 (max): FriendliAI, Baseten (FAST), Novita (FP8), Parasail (NVFP4), CoreWeave, Multiverse Computing, DeepInfra (FP4), Nebius (FP4), Together AI, Scaleway, Databricks, Bitdeer AI, Fireworks, GMI (FP8), Baseten, Modular, Zai, and Mistral.

All 19 providers of GLM-5.2 (max) support function calling (tool use).

The best provider for GLM-5.2 (max) depends on your priorities: Nebius (FP4) offers the highest output speed, Baseten (FAST) has the lowest latency, and Bitdeer AI 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

GLM-5.2 (max) API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Endpoint Accuracy

Endpoint Accuracy Index: GLM-5.2 (max)

Endpoint Accuracy Index

Pricing

Pricing: Cache Hit, Input, and Output

Cache Hit

Pricing: Blended Price

Price

Pricing: Cache Discount

Cache Price Discount

Output Speed vs. Price

Output Speed

Speed

Output Speed: GLM-5.2 (max)

Output Speed

Model Performance Representation

Latency vs. Output Speed

Output Speed

Latency

Time to First Answer Token: GLM-5.2 (max) Providers

Time to First Answer Token

Median

End-to-End Response Time

End-to-End Response Time: GLM-5.2 (max) Providers

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access GLM-5.2 (max)?

How many API providers offer GLM-5.2 (max)?

Which provider is fastest for GLM-5.2 (max)?

Which provider has the lowest latency for GLM-5.2 (max)?

Which provider is cheapest for GLM-5.2 (max)?

Which provider has the lowest input price for GLM-5.2 (max)?

Which provider has the lowest output price for GLM-5.2 (max)?

How much do prices vary across GLM-5.2 (max) providers?

How much does speed vary across GLM-5.2 (max) providers?

Which GLM-5.2 (max) providers support JSON mode?

Which GLM-5.2 (max) providers support function calling?

Which is the best provider for GLM-5.2 (max)?

How do I choose a provider for GLM-5.2 (max)?

Does provider performance for GLM-5.2 (max) change over time?

What are the overall capabilities of GLM-5.2 (max)?