Choose a model to open its comparison page.
GLM-5.2 benchmark, API pricing, and provider data cover 306 API providers, with prices starting at $0.0010/request. GLM-5.2 free API options are available from 7 providers. The page also shows measured API speed and first-token latency.
Zhipu GLM-5.2 is Zhipu latest flagship coding and agentic model with a 1M-token context window, enhanced reasoning modes, and long-horizon software engineering capabilities.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
2 metrics
2 metrics
15 metrics · Rated
11 metrics · Rated
4 metrics · Estimated
10 metrics · Provisional
5 metrics · Estimated
0 metrics · No data
1 metric · No data
1 metric · Provisional
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Alibaba alibaba/fast | $2.31/M | $7.26/M | 100.0% | — | — | 1.0M tokens / 131.1K tokens |
Z.AI z-ai/fp8 | $1.40/M | $4.40/M | 99.9% | — | — | 1.0M tokens / 131.1K tokens |
Cloudflare cloudflare/fast | $2.10/M | $6.60/M | 99.9% | — | — | 262.1K tokens / 262.1K tokens |
Decart decart/fp4 | $0.720/M | $1.80/M | 99.9% | — | — | 1.0M tokens / 1.0M tokens |
Wafer wafer | $1.26/M | $3.96/M | 99.8% | — | — | 1.0M tokens / 131.1K tokens |
Phala phala | $1.40/M | $4.40/M | 99.8% | — | — | 1.0M tokens / 131.1K tokens |
Novita novita/fp8 | $0.717/M | $2.25/M | 99.8% | — | — | 1.0M tokens / 131.1K tokens |
SiliconFlow siliconflow/fp8 | $1.19/M | $3.74/M | 99.8% | — | — | 1.0M tokens / 262.1K tokens |
Wafer wafer/fast | $2.10/M | $6.60/M | 99.8% | — | — | 1.0M tokens / 131.1K tokens |
Cloudflare cloudflare | $1.40/M | $4.40/M | 99.7% | — | — | 262.1K tokens / 262.1K tokens |
StreamLake streamlake/fp8 | $0.420/M | $1.32/M | 99.6% | — | — | 1.0M tokens / 128K tokens |
CoreWeave coreweave/fp4 | $0.760/M | $2.42/M | 99.5% | — | — | 262.1K tokens / 262.1K tokens |
Friendli friendli | $1.40/M | $4.40/M | 99.4% | — | — | 1.0M tokens / 1.0M tokens |
Fireworks fireworks | $1.40/M | $4.40/M | 99.4% | — | — | 1.0M tokens / — |
Parasail parasail/fp4 | $1.40/M | $4.40/M | 99.3% | — | — | 262.1K tokens / 262.1K tokens |
DeepInfra deepinfra/fp4 | $0.750/M | $2.40/M | 99.2% | — | — | 1.0M tokens / 131.1K tokens |
Alibaba alibaba/fp8 | $0.966/M | $3.04/M | 99.2% | — | — | 1.0M tokens / 131.1K tokens |
BaseTen baseten/fast | $2.10/M | $6.60/M | 99.2% | — | — | 524.3K tokens / 262.1K tokens |
GMICloud gmicloud/fp8 | $0.924/M | $2.90/M | 99.1% | — | — | 1.0M tokens / — |
BaseTen baseten/fp8 | $1.40/M | $4.40/M | 99.0% | — | — | 1.0M tokens / 262.1K tokens |
Inceptron inceptron/fp4 | $0.940/M | $2.90/M | 98.9% | — | — | 1.0M tokens / 1.0M tokens |
AtlasCloud atlas-cloud/fp8 | $1.26/M | $3.96/M | 98.7% | — | — | 1.0M tokens / 131.1K tokens |
Venice venice/fp8 | $1.40/M | $4.40/M | 98.6% | — | — | 1M tokens / 131.1K tokens |
Baidu baidu/fp8 | $0.756/M | $2.38/M | 98.6% | — | — | 1.0M tokens / 131.1K tokens |
DigitalOcean digitalocean | $1.05/M | $4.40/M | 98.5% | — | — | 262.1K tokens / — |
Fireworks fireworks/fast | $2.10/M | $6.60/M | 98.3% | — | — | 1.0M tokens / — |
Sail Research sail-research/fp8 | $1/M | $3.50/M | 98.3% | — | — | 1.0M tokens / 131.1K tokens |
Ionstream ionstream/fp4 | $1.40/M | $4.40/M | 97.9% | — | — | 1.0M tokens / 131.1K tokens |
Together together | $1.40/M | $4.40/M | 96.5% | — | — | 512K tokens / — |
Ambient ambient/fp8 | $1.05/M | $4.40/M | 95.5% | — | — | 202.8K tokens / 202.8K tokens |
Morph morph | $1.10/M | $4.10/M | 95.2% | — | — | 1.0M tokens / 1.0M tokens |
Chutes chutes/fp4 | $1.25/M | $3.95/M | 94.1% | — | — | 1.0M tokens / 65.5K tokens |
AkashML akashml/fp8 | $0.770/M | $2.42/M | 88.3% | — | — | 96.9K tokens / 96.9K tokens |
Compare GLM-5.2 API pricing across 299 providers. Prices range from $0.0010/request to $37500.00/M. X666 API offers the lowest rate at $0.0010/request. 7 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | glm-5.2 | glm | -69%$0.438/M Cache read$0.110/M | -65%$1.53/M | 36.3 t/s | 9.60 s | — | |
L1 100% | GLM-5.2-C | glm | $0.0027/request | - | — | — | ||
L1 100% | glm-5.2-20260613 | glm | -69%$0.438/M Cache read$0.110/M | -65%$1.53/M | — | — | — | |
L1 100% | glm-5.2 | 鱼干公益基础组 | -99%$0.020/M Cache read$0.020/M | -99%$0.040/M | 26.2 t/s | 16.25 s | ||
L1 0% | z-ai/glm-5.2 | default | -95%$0.068/M | -98%$0.068/M | 21.8 t/s | 13.00 s | ||
L1 100% | glm-5.2 | default | -61%$0.548/M Cache read$0.137/M | -56%$1.92/M | — | — | — | |
L1 100% | glm-5.2 | glm-sale | -55%$0.629/M Cache read$0.157/M | -50%$2.20/M | — | — | — | |
L1 100% | GLM-5.2 | default | $0.080/request | - | — | — | — | |
L1 100% | glm-5.2 | sale | $4.00/M | $14.00/M | — | — | — | |
L1 99% L2 0% | z-ai/glm-5.2 | default | -10%$1.26/M Cache read$2.00/M | -10%$3.96/M | — | — | — | |
L1 100% | glm-5.2 | default | -38%$0.870/M Cache read$0.156/M | -39%$2.70/M | — | — | ||
L1 100% | ZhipuAI/GLM-5.2 | default | $0.0014/request | - | — | — | — | |
L1 100% | [按次稳定]ZhipuAI/GLM-5.2 | default | $0.0055/request | - | — | — | — | |
L1 100% | glm-5.2 | default | -84%$0.219/M Cache read$0.055/MCache write$0.055/MCache write 1h$0.088/M | -83%$0.767/M | — | — | — | |
L1 100% | glm-5.2 | default | $8.00/M Cache read$2.00/M | $28.00/M | — | — | — | |
L1 100% L2 42% | glm-5.2 | Z-AI | $23.73/M Cache read$1.42/M | $71.17/M | — | — | — | |
L1 100% L2 100% | glm-5.2 | default | $75.00/M | $75.00/M | — | — | — | |
L1 100% | glm-5.2 | 🇨🇳国产官方模型 | $4.80/M Cache read$1.20/M | $16.80/M | — | — | — | |
L1 100% | glm-5.2 | default | $8.00/M Cache read$2.00/M | $28.00/M | — | — | — | |
兔子API Free | L1 100% | glm-5.2 | default | Free | Free | — | — | — |
