API MODEL RATE LIMIT.md•1.62 kB
**GEMINI MODELS RATE LIMITS**
Model RPM TPM RPD
Text-out models
Gemini 2.5 Pro 5 250,000 100
Gemini 2.5 Flash 10 250,000 250
Gemini 2.5 Flash-Lite 15 250,000 1,000
Gemini 2.0 Flash 15 1,000,000 200
Gemini 2.0 Flash-Lite 30 1,000,000 200
Multi-modal generation models
Gemini 2.5 Flash Preview TTS 3 10,000 15
Gemini 2.0 Flash Preview Image Generation 10 200,000 100
//i thinkg this two models below will be useful in our mcp server
Other models
Gemma 3 & 3n 30 15,000 14,400
Gemini Embedding 100 30,000 1,000
**OPENRoute MODELS RATE LIMITS**
🚀 OpenRouter Free Tier (No Credits Purchased)
You can use free-variant models (those with :free in the name, e.g. x-ai/grok-4-fast:free or deepseek/deepseek-r1:free).
Limits if you have 0 credits purchased:
50 requests per day total across free models.
20 requests per minute max.
1000 request per month total across free models.
That’s it — you won’t be able to exceed those until you add ≥ 10 credits (which unlocks up to 1,000 free-model requests/day).
So yes, there is a free tier, but it’s tiny unless you add at least a small payment.
**COHERENCE MODELS RATE LIMITS**
Cohere
Limits:
20 requests/minute
1,000 requests/month
Models share a common quota.
Command-A
Command-R7B
Command-R+
Command-R
Aya Expanse 8B
Aya Expanse 32B
Aya Vision 8B
Aya Vision 32B
**HUGGINGFACE MODELS RATE LIMITS**
Limits are like this:
unregistered: 1 req per hour
registered: 300 req her hour
pro: 1000 req per hour + access to fancy models
**NOTE:** Rate limits are subject to change. Please refer to the official documentation for the most up-to-date information.