Skip to main content
RapidDev - Software Development Agency
Reference Matrix · AI API Limits & Performance Matrix

AI API Limits & Performance34 model matrices, side by side

Rate limits, context windows, pricing and tier requirements for every major model — verified and kept current so you can size an API build before you write a line of code.

Building on an LLM API? Talk to us
34
Models
13
Providers
4.9Clutch rating
600+Happy partners
17+Countries served
190+Team members
AI-Powered Search

Describe your problem, we'll find the right matrix

Type in plain English — no need to know the exact matrix name

Showing 34 models

Yi-Large

GA
01.AI·32K–33K tokens context

Qwen2

GA
Alibaba·128K tokens (Qwen2-72B) context

Qwen3-Max

GA
Alibaba·262K tokens context

Claude 3 Haiku

GA
Anthropic·200K tokens context

Claude 3.5 Sonnet

GA
Anthropic·1M tokens context

Claude 4 Opus

GA
Anthropic·1M tokens (no surcharge) context

Claude 4 Sonnet

GA
Anthropic·1M tokens context

Cohere Command R

GA
Cohere·128K tokens context

Gemini 1.5 Flash

Deprecated
Google·1M tokens (retired) context

Gemini 1.5 Pro

Deprecated
Google·1M+ tokens (was the headline feature at launch) context

Gemini 2.5 Flash

Live
Google·1M tokens context

Gemini 2.5 Pro

Live
Google·1M+ tokens context

Gemma 2

Deprecated
Google·8K tokens (2B, 9B, 27B variants) context

Gemma 3

Live
Google·131K tokens context

Imagen 4

Deprecated
Google·n/a (image prompt) context

Llama 3

GA
Meta·8K–128K tokens (host-dependent) context

Llama 3.1

GA
Meta·128K tokens context

Llama 4 Maverick

GA
Meta·1M tokens (native); host-capped (Groq narrower; Fireworks ~1M) context

Llama 4 Scout

GA
Meta·10M tokens (native); 128K (Groq), 320K (DeepInfra), ~1M (Fireworks); full 10M only via self-hosting context

Phi-3

Deprecated
Microsoft·4K–128K tokens (depending on Phi-3 variant) context

Devstral

GA
Mistral AI·256K tokens context

Mistral Large

GA
Mistral AI·128K tokens context

Mistral Medium

GA
Mistral AI·128K tokens context

Mixtral 8x22B

GA
Mistral AI·65K tokens context

Mixtral 8x7B

GA
Mistral AI·32K tokens context

Kimi K2

GA
Moonshot AI·262K tokens (K2.6); 256K tokens (K2.7 Code) context

GPT-3.5 Turbo

GA
OpenAI·16K tokens (gpt-3.5-turbo-16k) / 4K tokens (base) context

GPT-4 Turbo

GA
OpenAI·128K tokens context

GPT-4o

GA
OpenAI·128K tokens context

GPT-5

GA
OpenAI·~1M tokens (922K input / 128K output) context

Stable Virtual Camera

Preview
Stability AI·n/a context

Falcon 180B

GA
TII·not published (2K-4K trained; some sources cite 8K — verify with TII before relying on this figure) context

Grok 2

Deprecated
xAI·not published for Grok 2 (retired); Grok 4.5 successor: 500K tokens context

Grok 4

Deprecated
xAI·500K tokens (requests >200K may bill at a higher unpublished rate) context

We put the rapid in RapidDev

Need a dedicated strategic tech and growth partner? Discover what RapidDev can do for your business! Book a call with our team to schedule a free, no-obligation consultation. We'll discuss your project and provide a custom quote at no cost.