Skip to main content
To maintain system stability and equitable access, our API enforces rate limiting—controlling how frequently an organization can send requests within a certain time window. API rate limits are defined in two ways:
  • TPM (Tokens per Minute) for LLM models
  • RPH (Requests per Hour) for video models
These limits are enforced at the organization level.

​
Usage Tiers and Auto Upgrades

Rate limits vary by usage tier, with each tier offering different quotas for each model. By default, organizations are assigned to Tier 1. As you buy credit from our platform, we automatically upgrade you to the next usage tier, using the following tier system. For example, after purchasing a $5 credit balance, you will be upgraded to Tier 2 within 24 hours. Please note that voucher redemptions do not count towards purchase.
Tier NameTotal Purchase AmountTime After
Tier 1$0Immediately
Tier 2$524 hours
Tier 3$5024 hours
Tier 4$20024 hours
Tier 5$100024 hours
If somehow you wish to request for a manual tier upgrade, please contact support@gmicloud.ai.

​
Rate Limit Table

Model NameTier 1 TPMTier 2 TPMTier 3 TPMTier 4 TPMTier 5 TPM
deepseek-ai/DeepSeek-R1100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Llama-8B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Distill-Llama-70B100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R1-Zero100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-R2100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-V3100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-V3-Base100,000450,000800,0002,000,00030,000,000
deepseek-ai/DeepSeek-V3-0324100,000450,000800,0002,000,000150,000,000
deepseek-ai/DeepSeek-V3.1100,0002,000,0004,000,00010,000,000150,000,000
deepseek-ai/DeepSeek-V3.1-Terminus100,0002,000,0004,000,00010,000,000150,000,000
deepseek-ai/DeepSeek-Prover-V2-671B100,000450,000800,0002,000,000150,000,000
deepseek-ai/DeepSeek-R1-0528100,0002,000,0004,000,00010,000,000150,000,000
meta-llama/Llama-3.1-8B100,0002,000,0004,000,00010,000,000150,000,000
meta-llama/Llama-3.3-70B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
meta-llama/Llama-4-Scout-17B-16E-Instruct100,0002,000,0004,000,00010,000,000150,000,000
meta-llama/Llama-4-Maverick-17B-128E-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/QwQ-32B100,0002,000,0004,000,00010,000,000150,000,000
Qwen/QwQ-32B-Preview100,0002,000,0004,000,00010,000,000150,000,000
Qwen/QwQ-32B-GGUF100,0002,000,0004,000,00010,000,000150,000,000
Qwen/QwQ-32B-AWQ100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-0.5B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-1.5B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct-1M100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct-AWQ100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct-GGUF100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-VL-7B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-Coder-7B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-Math-7B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-14B100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-14B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-14B-Instruct-AWQ100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-14B-Instruct-GGUF100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-Coder-14B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-32B100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-32B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen2.5-Coder-32B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-235B-A22B-FP8100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-32B-FP8100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-30B-A3B100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-Next-80B-A3B-Instruct100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-Next-80B-A3B-Thinking100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8100,0002,000,0004,000,00010,000,000150,000,000
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8100,0002,000,0004,000,00010,000,000150,000,000
moonshotai/Kimi-K2-Instruct100,0002,000,0004,000,00010,000,000150,000,000
moonshotai/Kimi-K2-Instruct-0905100,0002,000,0004,000,00010,000,000150,000,000
openai/gpt-oss-120b100,0002,000,0004,000,00010,000,000150,000,000
zai-org/GLM-4.5-FP8100,0002,000,0004,000,00010,000,000150,000,000
zai-org/GLM-4.5-Air-FP8100,0002,000,0004,000,00010,000,000150,000,000
zai-org/GLM-4.6100,0002,000,0004,000,00010,000,000150,000,000