Docs/AI SDK

AI

Models

Last updated April 17, 2026

Browse all supported AI models available through Cencori, including their providers, types, and context windows.

Overview

Cencori provides unified access to 100+ state-of-the-art AI models from leading providers like OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, and more.

You can use any of these models with the same API format, simply by changing the model parameter.

Model Catalog


105 models14 providers
Anthropic

Claude 3.5 Haiku

claude-3-5-haiku-20241022

chat
Anthropic200K ctx

Fast and efficient

Anthropic

Claude 3.5 Sonnet

claude-3-5-sonnet-20241022

chat
Anthropic200K ctx

Balance of speed and capability

Anthropic

Claude 3.7 Sonnet

claude-3-7-sonnet

reasoning
Anthropic200K ctx

Hybrid reasoning model

Anthropic

Claude Haiku 4.5

claude-haiku-4.5

chat
Anthropic200K ctx

Fastest Claude model

Anthropic

Claude Opus 4

claude-opus-4

chat
Anthropic200K ctx

Most capable Claude model

Anthropic

Claude Opus 4.5

claude-opus-4.5

chat
Anthropic200K ctx

Latest, most intelligent

Anthropic

Claude Opus 4.6

claude-opus-4.6

chat
Anthropic1M ctx

Latest flagship, agentic coding record-breaker

Anthropic

Claude Opus 4.7

claude-opus-4.7

chat
Anthropic1M ctx

Latest flagship, improved reasoning & agentic coding

Anthropic

Claude Sonnet 4

claude-sonnet-4

chat
Anthropic200K ctx

Balanced speed & capability

Anthropic

Claude Sonnet 4.5

claude-sonnet-4.5

chat
Anthropic200K ctx

Enhanced coding & agents

Anthropic

Claude Sonnet 4.6

claude-sonnet-4.6

chat
Anthropic200K ctx

Latest flagship, enhanced reasoning & coding

Cohere

Command A

command-a-03-2025

chat
Cohere256K ctx

Most performant, agentic tasks

Cohere

Command Light

command-light

chat
Cohere4K ctx

Fast and efficient

Cohere

Command R

command-r

chat
Cohere128K ctx

Balanced performance

Cohere

Command R+

command-r-plus-08-2024

chat
Cohere128K ctx

Complex RAG and multi-step

DeepSeek

DeepSeek Coder V2

deepseek-coder-v2

code
DeepSeek128K ctx

338 languages, GPT-4 level

DeepSeek

DeepSeek R1

deepseek-reasoner

reasoning
DeepSeek64K ctx

Reasoning model

DeepSeek

DeepSeek V3

deepseek-chat

chat
DeepSeek128K ctx

128K context, MIT license

DeepSeek

DeepSeek V3.1

deepseek-v3.1

chat
DeepSeek128K ctx

Hybrid thinking modes

DeepSeek

DeepSeek V3.2

deepseek-v3.2

chat
DeepSeek128K ctx

GPT-5 level, daily driver

DeepSeek

DeepSeek V3.2 Speciale

deepseek-v3.2-speciale

reasoning
DeepSeek128K ctx

Maxed reasoning, competition gold

Google

Gemini 2.0 Flash

gemini-2.0-flash

chat
Google AI1M ctx

Fast model

Google

Gemini 2.0 Flash Thinking

gemini-2.0-flash-thinking

reasoning
Google AI1M ctx

Reasoning variant

Google

Gemini 2.5 Flash

gemini-2.5-flash

chat
Google AI1M ctx

Thinking capabilities

Google

Gemini 2.5 Flash Lite

gemini-2.5-flash-lite

chat
Google AI1M ctx

Speed optimized

Google

Gemini 2.5 Pro

gemini-2.5-pro

chat
Google AI1M ctx

Enhanced reasoning & coding

Google

Gemini 3 Deep Think

gemini-3-deep-think

reasoning
Google AI1M ctx

Deep iterative reasoning

Google

Gemini 3 Flash

gemini-3-flash

chat
Google AI1M ctx

Frontier speed & intelligence

Google

Gemini 3 Pro

gemini-3-pro

chat
Google AI2M ctx

Powerful Gemini model

Google

Gemini 3 Pro Image

gemini-3-pro-image

image
Google AI ctx

Fast photorealism

Google

Gemini 3.1 Flash Image (Nano Banana 2)

gemini-3.1-flash-image

image
Google AI ctx

Reasoning-guided image synthesis, up to 4K

Google

Gemini 3.1 Pro (Custom Tools)

gemini-3.1-pro-preview-customtools

chat
Google AI1M ctx

Optimized for custom tools and bash

Google

Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

chat
Google AI1M ctx

Latest flagship preview, 1M context, enhanced reasoning

Google

Imagen 3

imagen-3

image
Google AI ctx

High quality images

Groq

Llama 3.1 8B Instant

llama-3.1-8b-instant

chat
Groq128K ctx

Ultra-fast inference

Groq

Llama 3.3 70B Versatile

llama-3.3-70b-versatile

chat
Groq128K ctx

Groq-hosted versatile Llama 3.3 model

Groq

Llama 4 Maverick

llama-4-maverick

chat
Groq256K ctx

Latest multimodal Llama

Groq

Llama 4 Scout

llama-4-scout

chat
Groq256K ctx

Advanced Llama 4 model

Groq

Mixtral 8x7B

mixtral-8x7b-32768

chat
Groq33K ctx

MoE architecture

HuggingFace

Llama 3.3 70B

meta-llama/Llama-3.3-70B-Instruct

chat
Hugging Face128K ctx

Via HF Inference

HuggingFace

Llama 4 Maverick

meta-llama/Llama-4-Maverick

chat
Hugging Face256K ctx

Via HF Inference

HuggingFace

Mistral Large 3

mistralai/Mistral-Large-3

chat
Hugging Face128K ctx

Via HF Inference

HuggingFace

Qwen 2.5 72B

Qwen/Qwen2.5-72B-Instruct

chat
Hugging Face32K ctx

Via HF Inference

Meta

Llama 3.1 405B

llama-3.1-405b

chat
Meta AI128K ctx

Largest open model

Meta

Llama 3.1 70B

llama-3.1-70b

chat
Meta AI128K ctx

Balanced performance

Meta

Llama 3.2 90B Vision

llama-3.2-90b-vision

chat
Meta AI128K ctx

Multimodal understanding

Meta

Llama 3.3 70B

llama-3.3-70b

chat
Meta AI128K ctx

Latest Llama 3 model

Meta

Llama 4 Maverick

llama-4-maverick

chat
Meta AI256K ctx

Latest multimodal flagship

Meta

Llama 4 Scout

llama-4-scout

chat
Meta AI256K ctx

Advanced reasoning

Mistral

Codestral 25.01

codestral-latest

code
Mistral AI256K ctx

2.5x faster code generation

Mistral

Devstral 2

devstral-latest

code
Mistral AI256K ctx

Frontier code agents

Mistral

Magistral Medium

magistral-medium

reasoning
Mistral AI128K ctx

Multimodal reasoning

Mistral

Ministral 3B

ministral-3b

chat
Mistral AI128K ctx

Compact edge model

Mistral

Ministral 8B

ministral-8b

chat
Mistral AI128K ctx

Small efficient model

Mistral

Mistral Large 3

mistral-large-latest

chat
Mistral AI128K ctx

675B params, best open-weight multimodal

Mistral

Mistral Medium 3.1

mistral-medium-latest

chat
Mistral AI128K ctx

Frontier-class multimodal

Mistral

Mistral Small 3

mistral-small-latest

chat
Mistral AI32K ctx

24B params, fast

OpenAI

DALL-E 2

dall-e-2

image
OpenAI ctx

Fast image generation

OpenAI

DALL-E 3

dall-e-3

image
OpenAI ctx

High quality images

OpenAI

GPT Image 1

gpt-image-1

image
OpenAI ctx

ChatGPT image generation model

OpenAI

GPT Image 1.5

gpt-image-1.5

image
OpenAI ctx

Best text rendering

OpenAI

GPT-4 Turbo

gpt-4-turbo

chat
OpenAI128K ctx

Legacy GPT-4 model

OpenAI

GPT-4.1

gpt-4.1

code
OpenAI1.0M ctx

Long-context GPT-4.1

OpenAI

GPT-4.1 Mini

gpt-4.1-mini

chat
OpenAI1.0M ctx

Balanced GPT-4.1 model

OpenAI

GPT-4.1 Nano

gpt-4.1-nano

chat
OpenAI1.0M ctx

Fast GPT-4.1 nano model

OpenAI

GPT-4o

gpt-4o

chat
OpenAI128K ctx

Omni-modal model

OpenAI

GPT-4o Mini

gpt-4o-mini

chat
OpenAI128K ctx

Fast and cost-effective

OpenAI

GPT-5

gpt-5

chat
OpenAI400K ctx

Flagship model

OpenAI

GPT-5 Mini

gpt-5-mini

chat
OpenAI400K ctx

Fast and efficient

OpenAI

GPT-5 Nano

gpt-5-nano

chat
OpenAI400K ctx

Lowest-latency GPT-5 model

OpenAI

GPT-5 Pro

gpt-5-pro

chat
OpenAI400K ctx

High-quality GPT-5 variant

OpenAI

GPT-5.1

gpt-5.1

chat
OpenAI400K ctx

Improved GPT-5 generation

OpenAI

GPT-5.2

gpt-5.2

chat
OpenAI400K ctx

Latest GPT-5.2 flagship

OpenAI

GPT-5.2 Pro

gpt-5.2-pro

chat
OpenAI400K ctx

Most capable GPT-5.2 variant

OpenAI

GPT-5.3 Instant

gpt-5.3-chat-latest

chat
OpenAI400K ctx

Latest GPT-5.3 instant release

OpenAI

GPT-5.4 Pro

gpt-5.4-pro

chat
OpenAI400K ctx

Most capable GPT-5.4 variant

OpenAI

GPT-5.4 Thinking

gpt-5.4

chat
OpenAI400K ctx

Latest GPT-5.4 reasoning model

OpenAI

o1

o1

reasoning
OpenAI200K ctx

Legacy reasoning model

OpenAI

o3

o3

reasoning
OpenAI200K ctx

Advanced reasoning model

OpenAI

o3 Mini

o3-mini

reasoning
OpenAI200K ctx

Fast reasoning model

OpenAI

o3 Pro

o3-pro

reasoning
OpenAI200K ctx

Most advanced reasoning model

OpenAI

o4 Mini

o4-mini

reasoning
OpenAI200K ctx

Successor to o1-mini

OpenRouter

Claude Opus 4.5 (via OpenRouter)

anthropic/claude-opus-4.5

chat
OpenRouter200K ctx

Unified billing

OpenRouter

Gemini 3 Pro (via OpenRouter)

google/gemini-3-pro

chat
OpenRouter2M ctx

Meta-provider

OpenRouter

GPT-5 (via OpenRouter)

openai/gpt-5

chat
OpenRouter256K ctx

Access any model

OpenRouter

Grok 4 (via OpenRouter)

x-ai/grok-4

chat
OpenRouter256K ctx

Access xAI models

Perplexity

Sonar

sonar

search
Perplexity128K ctx

Default web-connected

Perplexity

Sonar Large Online

llama-3.1-sonar-large-128k-online

search
Perplexity128K ctx

Web-connected search

Perplexity

Sonar Pro

sonar-pro

search
Perplexity128K ctx

Enhanced search, richer context

Perplexity

Sonar Reasoning Pro

sonar-reasoning-pro

reasoning
Perplexity128K ctx

Deep inference & research

Qwen

Qwen 2.5 32B

qwen2.5-32b-instruct

chat
Qwen128K ctx

Balanced performance

Qwen

Qwen 2.5 72B

qwen2.5-72b-instruct

chat
Qwen128K ctx

Flagship model

Qwen

Qwen 2.5 Coder 32B

qwen2.5-coder-32b

code
Qwen128K ctx

Code specialized

Qwen

QwQ 32B

qwq-32b-preview

reasoning
Qwen32K ctx

Reasoning model

together.ai

DeepSeek V3.1

deepseek-ai/DeepSeek-V3.1

chat
Together AI128K ctx

Hybrid reasoning

together.ai

Llama 3.3 70B Turbo

meta-llama/Llama-3.3-70B-Instruct-Turbo

chat
Together AI128K ctx

Fast Llama inference

together.ai

Llama 4 Maverick

meta-llama/Llama-4-Maverick

chat
Together AI256K ctx

Latest Llama

together.ai

Qwen 2.5 72B

Qwen/Qwen2.5-72B-Instruct-Turbo

chat
Together AI32K ctx

Alibaba flagship

Grok

Grok 3

grok-3

chat
xAI128K ctx

DeepSearch, Big Brain Mode

Grok

Grok 3 Mini

grok-3-mini

chat
xAI128K ctx

Fast responses

Grok

Grok 4

grok-4

chat
xAI256K ctx

Enhanced reasoning, real-time search

Grok

Grok 4 Heavy

grok-4-heavy

chat
xAI256K ctx

Maximum capability

Grok

Grok 4.1

grok-4.1

chat
xAI256K ctx

Improved multimodal & reasoning

Grok

Grok 4.1 Fast

grok-4.1-fast

chat
xAI2M ctx

Best agentic tool calling

Grok

Grok Code Fast

grok-code-fast-1

code
xAI128K ctx

Fast agentic coding

Usage

To use a model, pass its ID to any of the AI SDK methods:

Codetext
import { cencori } from '@/lib/cencori'
 
const result = await cencori.ai.chat({
  model: 'gpt-4o', // Use the ID from the catalog above
  messages: [
    { role: 'user', content: 'Hello!' }
  ]
})