•

Open weights model

•

Released June 2026

GLM-5.2 (max) API Provider Benchmarking & Analysis

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 Wafer, FriendliAI, Makora (NVFP4), Novita (FP8), Parasail (NVFP4), CoreWeave, Baseten, Together AI, DeepInfra (FP4), Nebius (FP4), Blackbox AI, Databricks, Scaleway, Crusoe (NVFP4), Fireworks, GMI (FP8), SiliconFlow (FP8).

Fastest

Baseten

571.8 t/s

Blackbox AI

460.4 t/s

Crusoe (NVFP4)

445.8 t/s

Nebius (FP4)

384.2 t/s

Together AI

373.0 t/s

Output speed

Total 17 providers

Lowest Latency

Baseten

4.37 s

Crusoe (NVFP4)

5.34 s

Nebius (FP4)

6.29 s

Blackbox AI

6.31 s

Together AI

6.75 s

Time to first answer token

Total 17 providers

Lowest Price

GMI (FP8)

$0.59

DeepInfra (FP4)

$0.61

Makora (NVFP4)

$0.66

Blackbox AI

$0.78

Wafer

$0.79

Blended price (per 1M tokens)

Total 17 providers

GLM-5.2 (max) is available through 17 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 (571.8 t/s), Blackbox AI (460.4 t/s), Crusoe (NVFP4) (445.8 t/s). Speed varies significantly across providers, with a 981% difference between the fastest and slowest.
For latency, Baseten (4.37s), Crusoe (NVFP4) (5.34s), Nebius (FP4) (6.29s) offer the lowest time to first answer token.
For pricing, GMI (FP8) (0.59), DeepInfra (FP4) (0.61), Makora (NVFP4) (0.66) offer the lowest blended prices per 1M tokens. Prices vary up to 4.2x across providers.
Baseten offers the best performance with both the highest speed and lowest latency. For cost optimization, GMI (FP8) provides the most competitive pricing.

Highlights

Speed

Output tokens per second · Higher is better

End-to-End Response Time

Seconds · Lower is better

Price

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

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

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.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

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).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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

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.

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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

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).

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).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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

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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

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).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

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).

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

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

For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.

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

Key Comparison Metrics & API Features



Wafer	205k	Open	$0.32	272	1.59	10.78	7.35
FriendliAI	1M	Open	$0.37	244	1.44	11.69	8.20
Makora	1M	Open	$0.44	135	0.82	19.38	14.85
Novita	1.05M	Open	$0.37	53	2.06	49.33	37.81
Parasail	1M	Open	--	221	1.25	12.58	9.06
CoreWeave	262k	Open	--	132	1.36	20.34	15.18
Baseten	261k	Open	--	572	0.88	5.25	3.50
Together AI	262k	Open	--	373	1.39	8.09	5.36
DeepInfra	1.05M	Open	--	67	0.85	38.35	30.00
Nebius	432k	Open	--	384	1.09	7.59	5.21
Blackbox AI	1.05M	Open	--	460	1.97	7.40	4.34
Databricks	1M	Open	--	335	1.05	8.50	5.96
Scaleway	262k	Open	--	103	1.51	25.71	19.36
Crusoe	262k	Open	$0.32	446	0.85	6.46	4.49
Fireworks	1M	Open	--	253	1.81	11.69	7.91
GMI	1.05M	Open	--	--	--	--	--
SiliconFlow	1.05M	Open	$0.58	64	1.72	40.88	31.32

Frequently Asked Questions

Common questions about GLM-5.2 (max) providers

GLM-5.2 (max) is available through 17 API providers: Wafer, FriendliAI, Makora (NVFP4), Novita (FP8), Parasail (NVFP4), CoreWeave, Baseten, Together AI, DeepInfra (FP4), Nebius (FP4), Blackbox AI, Databricks, Scaleway, Crusoe (NVFP4), Fireworks, GMI (FP8), and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.

GLM-5.2 (max) is currently available through 17 API providers that we benchmark and track.

The fastest providers for GLM-5.2 (max) by output speed are Baseten (571.8 t/s), Blackbox AI (460.4 t/s), and Crusoe (NVFP4) (445.8 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 (4.37s), Crusoe (NVFP4) (5.34s), and Nebius (FP4) (6.29s). Lower latency means faster initial response time.

The most affordable providers for GLM-5.2 (max) by blended price are GMI (FP8) ($0.59 per 1M tokens), DeepInfra (FP4) ($0.61 per 1M tokens), and Makora (NVFP4) ($0.66 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 Blackbox AI ($0.40 per 1M input tokens), GMI (FP8) ($0.92 per 1M input tokens), and DeepInfra (FP4) ($0.93 per 1M input tokens).

The providers with the lowest output token pricing for GLM-5.2 (max) are GMI (FP8) ($2.90 per 1M output tokens), DeepInfra (FP4) ($3.00 per 1M output tokens), and Makora (NVFP4) ($3.40 per 1M output tokens).

Prices for GLM-5.2 (max) vary up to 4.2x across providers. The most affordable is GMI (FP8) at $0.59 per 1M tokens, while Scaleway charges $2.52 per 1M tokens.

Output speed for GLM-5.2 (max) varies significantly across providers. Baseten is the fastest at 571.8 t/s, which is 10.8x faster than Novita (FP8) at 52.9 t/s.

16 of 17 providers support JSON mode for GLM-5.2 (max): Wafer, FriendliAI, Makora (NVFP4), Novita (FP8), Parasail (NVFP4), CoreWeave, Baseten, Together AI, DeepInfra (FP4), Nebius (FP4), Blackbox AI, Databricks, Scaleway, Crusoe (NVFP4), Fireworks, and GMI (FP8).

All 17 providers of GLM-5.2 (max) support function calling (tool use).

For GLM-5.2 (max), Baseten offers the best performance with highest speed and lowest latency. For cost optimization, 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

GLM-5.2 (max) API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

End-to-End Response Time

Price

Pricing

Pricing: Cache Hit, Input, and Output

Cache Hit

Input Price

Cache Pricing by Provider

Output Price

Pricing: Blended Price

Price

Cache Hit

Cache Pricing by Provider

Median

Pricing: Cache Discount

Cache Price Discount

Cache Hit

Cache Pricing by Provider

Median

Output Speed vs. Price

Output Speed

Price

Cache Hit

Cache Pricing by Provider

Median

Speed

Output Speed: GLM-5.2 (max)

Output Speed

Model Performance Representation

Latency vs. Output Speed

Output Speed

Latency (Time to First Token)

Price

Median

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

Standardized Reasoning Tokens

Median

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)?