|

Models

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


Z.ai

GLM-5.2

glm-5.2

Z.AI1M ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Anthropic

Claude Opus 5

claude-opus-5

Anthropic1M ctx
Input Cost$5.00 / 1M
Output Cost$25.00 / 1M
Anthropic

Claude Sonnet 5

claude-sonnet-5

Anthropic1M ctx
Input Cost$2.00 / 1M
Output Cost$10.00 / 1M
Google

Gemini 3.5 Flash

gemini-3.5-flash

Google1M ctx
Input Cost$1.50 / 1M
Output Cost$9.00 / 1M
OpenAI

GPT-5.6 Sol

gpt-5.6-sol

OpenAI1.1M ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.6 Terra

gpt-5.6-terra

OpenAI1.1M ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.6 Luna

gpt-5.6-luna

OpenAI1.1M ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.5

gpt-5.5

OpenAI1.1M ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.4 Thinking

gpt-5.4

OpenAI1.1M ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.4 Mini

gpt-5.4-mini

OpenAI400K ctx
Input Cost$0.15 / 1M
Output Cost$0.60 / 1M
OpenAI

GPT-5.4 Nano

gpt-5.4-nano

OpenAI400K ctx
Input Cost$0.05 / 1M
Output Cost$0.20 / 1M
OpenAI

GPT-5.4 Pro

gpt-5.4-pro

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.3 Instant

gpt-5.3-chat-latest

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.2 Pro

gpt-5.2-pro

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.2

gpt-5.2

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5.1

gpt-5.1

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5 Pro

gpt-5-pro

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5

gpt-5

OpenAI400K ctx
Input Cost$5.00 / 1M
Output Cost$15.00 / 1M
OpenAI

GPT-5 Mini

gpt-5-mini

OpenAI400K ctx
Input Cost$0.15 / 1M
Output Cost$0.60 / 1M
OpenAI

GPT-5 Nano

gpt-5-nano

OpenAI400K ctx
Input Cost$0.05 / 1M
Output Cost$0.20 / 1M
OpenAI

GPT-4.1

gpt-4.1

OpenAI1.0M ctx
Input Cost$2.50 / 1M
Output Cost$10.00 / 1M
OpenAI

GPT-4.1 Mini

gpt-4.1-mini

OpenAI1.0M ctx
Input Cost$0.15 / 1M
Output Cost$0.60 / 1M
OpenAI

GPT-4.1 Nano

gpt-4.1-nano

OpenAI1.0M ctx
Input Cost$0.05 / 1M
Output Cost$0.20 / 1M
OpenAI

GPT-4o

gpt-4o

OpenAI128K ctx
Input Cost$2.50 / 1M
Output Cost$10.00 / 1M
OpenAI

GPT-4o Mini

gpt-4o-mini

OpenAI128K ctx
Input Cost$0.15 / 1M
Output Cost$0.60 / 1M
OpenAI

o3

o3

OpenAI200K ctx
Input Cost$3.00 / 1M
Output Cost$12.00 / 1M
OpenAI

o3 Mini

o3-mini

OpenAI200K ctx
Input Cost$1.10 / 1M
Output Cost$4.40 / 1M
OpenAI

o4 Mini

o4-mini

OpenAI200K ctx
Input Cost$1.10 / 1M
Output Cost$4.40 / 1M
OpenAI

o1

o1

OpenAI200K ctx
Input Cost$3.00 / 1M
Output Cost$12.00 / 1M
OpenAI

GPT Image 2

gpt-image-2

OpenAI ctx
Input Cost$0.040
Output Costper img
OpenAI

GPT Image 1.5

gpt-image-1.5

OpenAI ctx
Input Cost$0.020
Output Costper img
OpenAI

GPT Image 1

gpt-image-1

OpenAI ctx
Input Cost$0.020
Output Costper img
Anthropic

Claude Fable 5

claude-fable-5

Anthropic1M ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Anthropic

Claude Opus 4.8

claude-opus-4-8

Anthropic1M ctx
Input Cost$15.00 / 1M
Output Cost$75.00 / 1M
Anthropic

Claude Opus 4.7

claude-opus-4-7

Anthropic1M ctx
Input Cost$15.00 / 1M
Output Cost$75.00 / 1M
Anthropic

Claude Sonnet 4.6

claude-sonnet-4-6

Anthropic1M ctx
Input Cost$3.00 / 1M
Output Cost$15.00 / 1M
Anthropic

Claude Opus 4.6

claude-opus-4-6

Anthropic1M ctx
Input Cost$15.00 / 1M
Output Cost$75.00 / 1M
Anthropic

Claude Opus 4.5

claude-opus-4-5

Anthropic200K ctx
Input Cost$15.00 / 1M
Output Cost$75.00 / 1M
Anthropic

Claude Sonnet 4.5

claude-sonnet-4-5

Anthropic200K ctx
Input Cost$3.00 / 1M
Output Cost$15.00 / 1M
Anthropic

Claude Haiku 4.5

claude-haiku-4-5

Anthropic200K ctx
Input Cost$0.25 / 1M
Output Cost$1.25 / 1M
Google

Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

Google1M ctx
Input Cost$1.25 / 1M
Output Cost$5.00 / 1M
Google

Gemini 3.1 Pro (Custom Tools)

gemini-3.1-pro-preview-customtools

Google1M ctx
Input Cost$1.25 / 1M
Output Cost$5.00 / 1M
Google

Gemini 3.1 Flash Image (Nano Banana 2)

gemini-3.1-flash-image

Google ctx
Input Cost$0.020
Output Costper img
Google

Gemini 3 Flash Preview

gemini-3-flash-preview

Google1M ctx
Input Cost$0.075 / 1M
Output Cost$0.30 / 1M
Google

Gemini 2.5 Pro

gemini-2.5-pro

Google1M ctx
Input Cost$1.25 / 1M
Output Cost$5.00 / 1M
Google

Gemini 2.5 Flash

gemini-2.5-flash

Google1M ctx
Input Cost$0.075 / 1M
Output Cost$0.30 / 1M
Google

Gemini 2.5 Flash Lite

gemini-2.5-flash-lite

Google1M ctx
Input Cost$0.075 / 1M
Output Cost$0.30 / 1M
Google

Gemini 3 Pro Image

gemini-3-pro-image

Google ctx
Input Cost$0.020
Output Costper img
Mistral

Mistral Large 3

mistral-large-latest

Mistral AI128K ctx
Input Cost$2.00 / 1M
Output Cost$6.00 / 1M
Mistral

Mistral Medium 3.1

mistral-medium-latest

Mistral AI128K ctx
Input Cost$1.00 / 1M
Output Cost$3.00 / 1M
Mistral

Mistral Small 3

mistral-small-latest

Mistral AI32K ctx
Input Cost$0.20 / 1M
Output Cost$0.60 / 1M
Mistral

Ministral 3B

ministral-3b

Mistral AI128K ctx
Input Cost$0.06 / 1M
Output Cost$0.18 / 1M
Mistral

Ministral 8B

ministral-8b

Mistral AI128K ctx
Input Cost$0.20 / 1M
Output Cost$0.60 / 1M
Mistral

Codestral 25.01

codestral-latest

Mistral AI256K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Mistral

Devstral 2

devstral-latest

Mistral AI256K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Mistral

Magistral Medium

magistral-medium

Mistral AI128K ctx
Input Cost$1.00 / 1M
Output Cost$3.00 / 1M
Groq

Llama 3.3 70B Versatile

Free

llama-3.3-70b-versatile

Groq128K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Groq

Llama 3.1 8B Instant

Free

llama-3.1-8b-instant

Groq128K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Groq

GPT OSS 120B

openai/gpt-oss-120b

Groq131K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Groq

GPT OSS 20B

openai/gpt-oss-20b

Groq131K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Groq

Compound

Free

groq/compound

Groq131K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Groq

Compound Mini

Free

groq/compound-mini

Groq131K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Groq

Allam 2 7B

allam-2-7b

Groq131K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Cohere

Command R+

command-r-plus-08-2024

Cohere128K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Cohere

Command Light

command-light

Cohere4K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
together.ai

Llama 4 Maverick

meta-llama/Llama-4-Maverick

Together AI256K ctx
Input Cost$2.66 / 1M
Output Cost$2.66 / 1M
together.ai

Llama 3.3 70B Turbo

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

Together AI128K ctx
Input Cost$0.70 / 1M
Output Cost$0.90 / 1M
together.ai

Qwen 2.5 72B

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

Together AI32K ctx
Input Cost$0.40 / 1M
Output Cost$0.40 / 1M
together.ai

DeepSeek V3.1

deepseek-ai/DeepSeek-V3.1

Together AI128K ctx
Input Cost$0.14 / 1M
Output Cost$0.28 / 1M
Perplexity

Sonar Pro

sonar-pro

Perplexity128K ctx
Input Cost$1.50 / 1M
Output Cost$4.50 / 1M
Perplexity

Sonar

sonar

Perplexity128K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Perplexity

Sonar Reasoning Pro

sonar-reasoning-pro

Perplexity128K ctx
Input Cost$1.50 / 1M
Output Cost$4.50 / 1M
OpenRouter

GPT-5 (via OpenRouter)

openai/gpt-5

OpenRouter256K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
OpenRouter

Claude Opus 4.5 (via OpenRouter)

anthropic/claude-opus-4.5

OpenRouter200K ctx
Input Cost$15.00 / 1M
Output Cost$75.00 / 1M
OpenRouter

Gemini 3 Pro (via OpenRouter)

google/gemini-3-pro

OpenRouter2M ctx
Input Cost$1.25 / 1M
Output Cost$5.00 / 1M
OpenRouter

Grok 4.3 (via OpenRouter)

x-ai/grok-4.3

OpenRouter1M ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
OpenRouter

Grok 4 (via OpenRouter)

x-ai/grok-4

OpenRouter256K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Grok

Grok 4.6

grok-4.6

xAI500K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Grok

Grok 4.5

grok-4.5

xAI500K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Grok

Grok 4.3

grok-4.3

xAI1M ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Meta

Llama 4 Maverick

llama-4-maverick

Meta AI256K ctx
Input Cost$2.66 / 1M
Output Cost$2.66 / 1M
Meta

Llama 4 Scout

llama-4-scout

Meta AI256K ctx
Input Cost$0.70 / 1M
Output Cost$0.90 / 1M
Meta

Llama 3.3 70B

llama-3.3-70b

Meta AI128K ctx
Input Cost$0.70 / 1M
Output Cost$0.90 / 1M
Meta

Llama 3.2 90B Vision

llama-3.2-90b-vision

Meta AI128K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Meta

Llama 3.1 405B

llama-3.1-405b

Meta AI128K ctx
Input Cost$2.66 / 1M
Output Cost$2.66 / 1M
Meta

Llama 3.1 70B

llama-3.1-70b

Meta AI128K ctx
Input Cost$0.70 / 1M
Output Cost$0.90 / 1M
Qwen

Qwen 2.5 72B

qwen2.5-72b-instruct

Qwen128K ctx
Input Cost$0.40 / 1M
Output Cost$0.40 / 1M
Qwen

Qwen 2.5 32B

qwen2.5-32b-instruct

Qwen128K ctx
Input Cost$0.20 / 1M
Output Cost$0.20 / 1M
Qwen

Qwen 2.5 Coder 32B

qwen2.5-coder-32b

Qwen128K ctx
Input Cost$0.20 / 1M
Output Cost$0.20 / 1M
Qwen

QwQ 32B

qwq-32b-preview

Qwen32K ctx
Input Cost$0.20 / 1M
Output Cost$0.20 / 1M
DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

DeepSeek1M ctx
Input Cost$0.14 / 1M
Output Cost$0.28 / 1M
DeepSeek

DeepSeek V4 Flash

deepseek-v4-flash

DeepSeek1M ctx
Input Cost$0.07 / 1M
Output Cost$0.14 / 1M
Cerebras

GPT OSS 120B (Cerebras)

Free

gpt-oss-120b

Cerebras131K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Cerebras

Z.AI GLM 4.7 (Cerebras)

Free

zai-glm-4.7

Cerebras131K ctx
Input Cost$0.00 / 1M
Output Cost$0.00 / 1M
Cerebras

Gemma 4 31B (Cerebras)

gemma-4-31b

vision
Cerebras131K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Maximo AI

Maximo Atlas 1.1

maximo-atlas-1.1

Maximo AI262K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M
Helix

Helix Advisor

helix-advisor

Helix128K ctx
Input Cost$0.50 / 1M
Output Cost$1.50 / 1M

Usage

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

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!' }
  ]
})