Concentrate AI

concentrate

Updated 55 minutes ago

Concentrate AI is an LLM aggregator and proxy that provides a unified OpenAI-compatible API for accessing models from multiple providers including Anthropic, OpenAI, Google, xAI, DeepSeek, Alibaba, Moonshot, Mistral, Meta, and others. It offers 156+ models through a single endpoint.

Visit Website LLMs.txt

Browse 142 LLM models available from Concentrate AI. Compare prices and features.

Models (142)

Organization	Model Name	Original Model	Input	Output
Anthropic	Claude Opus 5	`claude-opus-5`	-	-	View
OpenAI	GPT-5.6 Sol	`gpt-5.6-sol`	-	-	View
Moonshot AI	Kimi K3	`kimi-k3`	-	-	View
OpenAI	GPT-5.6 Luna	`gpt-5.6-luna`	-	-	View
Alibaba	Qwen3.8 Max	`qwen3.8-max`	-	-	View
OpenAI	GPT-5.6 Terra	`gpt-5.6-terra`	-	-	View
Anthropic	Claude Sonnet 5	`claude-sonnet-5`	-	-	View
SpaceXAI	Grok 4.5	`grok-4.5`	-	-	View
Z.ai	GLM-5.2	`glm-5.2`	-	-	View
Anthropic	Claude Fable 5	`claude-fable-5`	-	-	View
SpaceXAI	Grok Build 0.1 0616	`grok-build-0.1`	-	-	View
Anthropic	Claude Opus 4.8	`claude-opus-4-8`	-	-	View
Tencent	Hy3-preview	`hy3`	-	-	View
google	Gemini 3.5 Flash-Lite	`gemini-3.5-flash-lite`	-	-	View
Minimax	MiniMax M3	`minimax-m3`	-	-	View
Cohere	Command A+	`command-a`	-	-	View
qwen	Qwen: Qwen3.6 Flash	`qwen3.6-flash`	-	-	View
SpaceXAI	Grok 4.3	`grok-4.3`	-	-	View
Alibaba	Qwen3.7-Plus	`qwen3.7-plus`	-	-	View
DeepSeek	DeepSeek-V4-Pro-Max	`deepseek-v4-pro`	-	-	View
qwen	Qwen3.7 Max	`qwen3.7-max`	-	-	View
OpenAI	GPT-5.5	`gpt-5.5`	-	-	View
Anthropic	Claude Opus 4.7	`claude-opus-4-7`	-	-	View
DeepSeek	DeepSeek V4 Flash	`deepseek-v4-flash-0423`	-	-	View
DeepSeek	DeepSeek V4 Flash	`deepseek-v4-flash-0731`	-	-	View
Xiaomi	MiMo-V2.5	`mimo-v2.5`	-	-	View
google	Gemini 3.5 Flash	`gemini-3.5-flash`	-	-	View
Moonshot AI	Kimi K2.7 Code	`kimi-k2-7-code`	-	-	View
Moonshot AI	Kimi K2.6	`kimi-k2-6`	-	-	View
SpaceXAI	Grok 4.20 0309 v2	`grok-4.20-non-reasoning`	-	-	View
Xiaomi	MiMo-V2.5-Pro	`mimo-v2.5-pro`	-	-	View
Z.ai	GLM-5.1	`glm-5.1`	-	-	View
qwen	Qwen3.6 Plus	`qwen3.6-plus`	-	-	View
google	Gemini 3.1 Pro	`gemini-3.1-pro-preview`	-	-	View
OpenAI	GPT-5.4 mini	`gpt-5.4-mini`	-	-	View
OpenAI	GPT-5.4	`gpt-5.4`	-	-	View
OpenAI	GPT-5.4 nano	`gpt-5.4-nano`	-	-	View
Anthropic	Claude Opus 4.6	`claude-opus-4-6`	-	-	View
Anthropic	Claude Sonnet 4.6	`claude-sonnet-4-6`	-	-	View
Minimax	MiniMax M2.5	`minimax-m2-5`	-	-	View
Minimax	MiniMax M2.7	`minimax-m2-7`	-	-	View
google	Gemini 3.1 Flash-Lite	`gemini-3.1-flash-lite-preview`	-	-	View
qwen	Qwen3.5-122B-A10B	`qwen3.5-122b-a10b`	-	-	View
qwen	Qwen3.5-35B-A3B	`qwen3.5-35b-a3b`	-	-	View
Z.ai	GLM-5	`glm-5`	-	-	View
qwen	Qwen3.5-397B-A17B	`qwen3.5-397b-a17b`	-	-	View
StepFun	Step-3.5-Flash	`step-3-5-flash`	-	-	View
Moonshot AI	Kimi K2.5	`kimi-k2-5`	-	-	View
google	Gemini 3 Flash Preview	`gemini-3-flash-preview`	-	-	View
OpenAI	GPT-5.2	`gpt-5.2`	-	-	View
Z.ai	GLM-4.7	`glm-4.7`	-	-	View
Anthropic	Claude Opus 4.5	`claude-opus-4-5`	-	-	View
Minimax	MiniMax M2.1	`minimax-m2-1`	-	-	View
OpenAI	GPT-5.1 Thinking	`gpt-5.1`	-	-	View
DeepSeek	DeepSeek-V3.2	`deepseek-v3-2`	-	-	View
Amazon	Nova 2 Lite	`nova-2-lite`	-	-	View
Z.ai	GLM-4.7-Flash	`glm-4.7-flash`	-	-	View
Anthropic	Claude 4.5 Sonnet	`claude-sonnet-4-5`	-	-	View
Anthropic	Claude 4.5 Haiku	`claude-haiku-4-5`	-	-	View
qwen	Qwen3 Max Thinking	`qwen3-max`	-	-	View
Z.ai	GLM-4.6	`glm-4.6`	-	-	View
Minimax	MiniMax M2	`minimax-m2`	-	-	View
qwen	Qwen3 VL 235B A22B	`qwen3-vl-235b-a22b`	-	-	View
OpenAI	GPT-5	`gpt-5`	-	-	View
Anthropic	Claude 4.1 Opus	`claude-opus-4-1`	-	-	View
qwen	Qwen3-Next-80B-A3B-Thinking	`qwen3-next-80b-a3b`	-	-	View
OpenAI	GPT-5 mini	`gpt-5-mini`	-	-	View
OpenAI	GPT OSS 120B	`gpt-oss-120b`	-	-	View
OpenAI	GPT OSS 20B	`gpt-oss-20b`	-	-	View
OpenAI	GPT-5 nano	`gpt-5-nano`	-	-	View
google	Gemini 2.5 Pro Preview 06-05	`gemini-2.5-pro`	-	-	View
Z.ai	GLM-4.5	`glm-4.5`	-	-	View
DeepSeek	DeepSeek-R1-0528	`deepseek-r1`	-	-	View
DeepSeek	DeepSeek-R1-0528	`deepseek-r1-0528`	-	-	View
Anthropic	Claude 4 Sonnet	`claude-sonnet-4`	-	-	View
qwen	Qwen3 32B	`qwen3-32b`	-	-	View
google	Gemini 2.5 Flash	`gemini-2.5-flash`	-	-	View
google	Gemini 2.5 Flash-Lite	`gemini-2.5-flash-lite`	-	-	View
OpenAI	o4-mini	`o4-mini`	-	-	View
OpenAI	o3	`o3`	-	-	View
SpaceXAI	Grok-3 Mini	`grok-3-mini`	-	-	View
Mistral	Mistral Nemo	`mistral-nemo`	-	-	View
OpenAI	GPT-4.1 mini	`gpt-4.1-mini`	-	-	View
OpenAI	GPT-4.1	`gpt-4.1`	-	-	View
Meta	Llama 4 Scout	`llama-4-scout`	-	-	View
OpenAI	o3-mini	`o3-mini`	-	-	View
OpenAI	o1	`o1`	-	-	View
Meta	Llama 4 Maverick	`llama-4-maverick`	-	-	View
qwen	QwQ-32B	`qwq-32b`	-	-	View
Meta	Llama 3.1 8B Instruct	`llama-3.1-8b-instruct`	-	-	View
OpenAI	GPT-4o mini	`gpt-4o-mini`	-	-	View
Meta	Llama 3.1 70B Instruct	`llama-3.1-70b-instruct`	-	-	View
OpenAI	GPT-4o	`gpt-4o`	-	-	View
Meta	Llama 3.3 70B Instruct	`llama-3.3-70b-instruct`	-	-	View
Amazon	Nova Pro	`nova-pro`	-	-	View
Amazon	Nova Lite	`nova-lite`	-	-	View
Amazon	Nova Micro	`nova-micro`	-	-	View
AI21	Jamba 1.5 Large	`jamba-1-5-large`	-	-	View
AI21	Jamba 1.5 Mini	`jamba-1-5-mini`	-	-	View
qwen	Qwen: Qwen3.7 Flash	`qwen3.7-flash`	-	-	View
google	Gemini 3.6 Flash	`gemini-3.6-flash`	-	-	View
StepFun	Step 3.7 Flash	`step-3-7-flash`	-	-	View
google	Gemma 4 31B	`gemma-4-31b`	-	-	View
Minimax	MiniMax-M2.7-highspeed	`minimax-m2-7-highspeed`	-	-	View
SpaceXAI	Grok 4.20 (Reasoning)	`grok-4.20-0309-reasoning`	-	-	View
SpaceXAI	Grok 4.20 Multi-Agent	`grok-4.20-multi-agent-0309`	-	-	View
OpenAI	GPT-5.4 Pro	`gpt-5.4-pro`	-	-	View
qwen	Qwen3.5-Flash	`qwen3.5-flash`	-	-	View
qwen	Qwen3.5 Plus 2026-02-15	`qwen3.5-plus`	-	-	View
Minimax	MiniMax-M2.5-highspeed	`minimax-m2-5-highspeed`	-	-	View
OpenAI	GPT-5.3 Codex	`gpt-5.3-codex`	-	-	View
qwen	Qwen3 Coder Next	`qwen3-coder-next`	-	-	View
Z.ai	GLM-4.6V	`glm-4.6v`	-	-	View
Moonshot AI	Kimi K2 Thinking	`kimi-k2-thinking`	-	-	View
OpenAI	gpt-oss-safeguard-20b	`gpt-oss-safeguard-20b`	-	-	View
Alibaba	Qwen3 Coder Plus	`qwen3-coder-plus`	-	-	View
Alibaba	Qwen3-VL Plus	`qwen3-vl-plus`	-	-	View
Alibaba	Qwen3 Coder Flash	`qwen3-coder-flash`	-	-	View
Alibaba	qwen-plus-0125	`qwen-plus`	-	-	View
Mistral	Mistral Medium 3.1	`mistral-medium-3.1`	-	-	View
Z.ai	GLM-4.5V	`glm-4.5v`	-	-	View
Cohere	Command A Vision	`command-a-vision`	-	-	View
Alibaba	Qwen3 Coder 30B A3B Instruct	`qwen3-coder-30b-a3b`	-	-	View
Alibaba	Qwen Flash	`qwen-flash`	-	-	View
Mistral	Mistral Medium 3	`mistral-medium-3`	-	-	View
Meta	llama-3.2-1b-instruct	`llama-3.2-1b-instruct`	-	-	View
Mistral	Codestral (latest)	`codestral`	-	-	View
Meta	llama-3-70b-instruct	`llama-3-70b-instruct`	-	-	View
Meta	llama-3-8b-instruct	`llama-3-8b-instruct`	-	-	View
Mistral	Devstral 2	`devstral-2`	-	-	View
google	Gemma 3 12B Instruct	`gemma-3-12b`	-	-	View
google	Gemma 3 27B Instruct	`gemma-3-27b`	-	-	View
google	Gemma 3 4B Instruct	`gemma-3-4b`	-	-	View
google	Gemma 4 26B	`gemma-4-26b`	-	-	View
Mistral	Ministral 3 14B	`ministral-3-14b`	-	-	View
Mistral	Ministral 3 3B	`ministral-3-3b`	-	-	View
Mistral	Ministral 3 8B	`ministral-3-8b`	-	-	View
Mistral	Mistral Large 3	`mistral-large-3`	-	-	View
Mistral	Mistral Small 3.1	`mistral-small-3.1`	-	-	View
Mistral	Mistral Small 3.2	`mistral-small-3.2`	-	-	View
Amazon	Nova Premier	`nova-premier`	-	-	View
Alibaba	Qwen3 30B	`qwen3-30b`	-	-	View

Back to Providers Visit Website