Infercom Model Rate Limits

Rate limits are a mechanism to help manage Infercom API usage to provide stable performance and reliable service. They limit how many times each user can call the Infercom API within a given interval.

Rate limits are measured in:

• RPM: Requests per minute
• RPD: Requests per day

Basics

• A request is defined by a call to our API
• You can hit either limit type (RPM or RPD) depending on which one you reach first
• You will be notified in every request response what the status of your rate limits are (see rate limit response headers for more information)
• If you hit a rate limit, you will be sent an error message in your response (see API error codes)
• Check the Infercom Status Page for real-time platform and model availability

Infercom Inference Service rate limit tiers

There are a few different rate limit tier offerings we provide:

• Free Tier: Applied when there is no payment method linked with your account
• Developer Tier: Applied when a payment method is linked with your account
• Enterprise Tier: Higher limits for production workloads

Note

Please see the Billing page to link a payment method to your account.

Below are our rate limits by tier.

Model rate limits

Free Tier

EU-hosted models (sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
OpenAI	gpt-oss-120b	EU	20	20
Google	gemma-4-31B-it	EU	20	20
OpenAI	Whisper-Large-v3	EU	20	20
Mistral	E5-Mistral-7B-Instruct	EU	20	20

Global Model Catalog (non-sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
DeepSeek	DeepSeek-V3.1	Non-EU	20	20
DeepSeek	DeepSeek-V3.2	Non-EU	20	20
Meta	Meta-Llama-3.3-70B-Instruct	Non-EU	20	20
MiniMax	MiniMax-M3	Non-EU	20	20

Developer Tier

EU-hosted models (sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
OpenAI	gpt-oss-120b	EU	150	50,000
Google	gemma-4-31B-it	EU	80	20,000
OpenAI	Whisper-Large-v3	EU	150	50,000
Mistral	E5-Mistral-7B-Instruct	EU	150	50,000

Global Model Catalog (non-sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
DeepSeek	DeepSeek-V3.1	Non-EU	30	15,000
DeepSeek	DeepSeek-V3.2	Non-EU	60	12,000
Meta	Meta-Llama-3.3-70B-Instruct	Non-EU	120	30,000
MiniMax	MiniMax-M3	Non-EU	80	20,000

Enterprise Tier

Default limits for Enterprise tier. Custom limits available based on workload requirements - contact sales.

EU-hosted models (sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
OpenAI	gpt-oss-120b	EU	500	100,000
Google	gemma-4-31B-it	EU	250	50,000
OpenAI	Whisper-Large-v3	EU	500	100,000
Mistral	E5-Mistral-7B-Instruct	EU	500	100,000

Global Model Catalog (non-sovereign)

Developer	Model ID	Region	Requests per minute (RPM)	Requests per day (RPD)
DeepSeek	DeepSeek-V3.1	Non-EU	70	30,000
DeepSeek	DeepSeek-V3.2	Non-EU	80	-
Meta	Meta-Llama-3.3-70B-Instruct	Non-EU	400	75,000
MiniMax	MiniMax-M3	Non-EU	250	50,000

Note

Need custom limits? Enterprise customers can request custom rate limits based on workload requirements. Contact sales to discuss your needs.

Rate limit response headers

These headers are found in every request response and give information about the current status of rate limit usage.

RPM (Requests per minute):

• x-ratelimit-limit-requests
  • The maximum number of requests allowed per minute.
• x-ratelimit-remaining-requests
  • The number of requests remaining in the current minute before hitting the rate limit.
• x-ratelimit-reset-requests
  • Time in epoch time until the per-minute request quota resets.

RPD (Requests per day):

• x-ratelimit-limit-requests-day
  • The maximum number of requests allowed per day.
• x-ratelimit-remaining-requests-day
  • The number of requests remaining in the current day before hitting the rate limit.
• x-ratelimit-reset-requests-day
  • Time in epoch time until the per-day request quota resets.