AI Model Catalog: 3672 Models Compared — Pricing, Context & Benchmarks

Anthropic: Claude Haiku 3.5 T

Tools

Fast Claude model for responsive assistance, classification, and lightweight agents

anthropic/claude-3-5-haiku-20241022 2024-10-22 200K context $0.8/M input $4/M output

3 providers

Anthropic: Claude Sonnet 3.5 v2 T

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-3-5-sonnet-20241022 2024-10-22 200K context Input not listed Output not listed

1 provider

Mistral AI: Ministral 8B Instruct T

Open weights

Efficient open Mistral edge model for on-device chat and function calling

mistral/ministral-8b-instruct-2410 2024-10-16 131.072K context Input not listed Output not listed

1 provider

Mistral AI: Ministral 3B T

Tools Open weights

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

mistral/ministral-3b 2024-10-16 128K context $0.04/M input $0.04/M output

6 providers

Writer: Palmyra X4 T

Tools

Enterprise language model for workflow automation, coding, data analysis, and tool use

writer/palmyra-x4 2024-10-09 128K context $2.5/M input $10/M output

2 providers

Meta: Llama-3.2-1B T

Open weights

Compact open Llama base model for lightweight and on-device use

meta/llama-3.2-1b 2024-09-25 131.072K context Input not listed Output not listed

1 provider

Meta: Llama-3.2-3B T

Open weights

Small open Llama base model for lightweight text generation and self-hosting

meta/llama-3.2-3b 2024-09-25 131.072K context Input not listed Output not listed

1 provider

Meta: Llama-3.2-11B-Vision-Instruct T

Tools Open weights

Open multimodal Llama model for image understanding, captioning, and visual QA

meta/llama-3.2-11b-vision-instruct 2024-09-25 128K context $0.055/M input $0.055/M output

3 providers

Meta: Llama 3.2 1B Instruct T

Open weights

Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants

meta/llama-3.2-1b-instruct 2024-09-25 131.072K context $0.01/M input $0.01/M output

7 providers

Meta: Llama-3.2-90B-Vision-Instruct T

Tools Open weights

Large open multimodal Llama model for image reasoning, document QA, and captioning

meta/llama-3.2-90b-vision-instruct 2024-09-25 128K context Input not listed Output not listed

1 provider

Meta: Llama 3.2 3B Instruct T

JSON Open weights

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

meta/llama-3.2-3b-instruct 2024-09-25 131.072K context $0.02/M input $0.02/M output

6 providers

Alibaba Qwen: Qwen2.5 7B Instruct T

Tools JSON Open weights

Small open Qwen2.5 instruction model for chat, structured output, and tool use

alibaba/qwen2.5-7b-instruct 2024-09-19 131.072K context $0.1/M input $0.2/M output

3 providers

Mistral AI: Pixtral 12B T

Tools Open weights

Mistral vision-language model for image understanding and multimodal chat

mistral/pixtral-12b 2024-09-11 128K context $0.15/M input $0.15/M output

4 providers

Cohere: Command R T

Tools Open weights

Cohere retrieval model for long-context chat and enterprise RAG workflows

cohere/command-r-08-2024 2024-08-30 128K context $0.15/M input $0.6/M output

8 providers

Cohere: Command R+ T

Tools Open weights

Cohere's RAG workhorse for long-context enterprise search and tool use

cohere/command-r-plus-08-2024 2024-08-30 128K context $2.5/M input $10/M output

10 providers

Sao10K: Llama 3.1 Euryale 70B v2.2 T

Tools JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

sao10k/l3.1-euryale-70b 2024-08-28 131.072K context $0.85/M input $0.85/M output

3 providers

NVIDIA: Nemotron Mini 4B Instruct T

Open weights

Compact Nemotron model for efficient reasoning and deployable AI agents

nvidia/nemotron-mini-4b-instruct 2024-08-21 128K context Input not listed Output not listed

1 provider

Nousresearch: Hermes 3 70B Instruct T

JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

nousresearch/hermes-3-llama-3.1-70b 2024-08-18 131.072K context $0.7/M input $0.7/M output

3 providers

Nousresearch: Hermes 3 405B Instruct T

JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

nousresearch/hermes-3-llama-3.1-405b 2024-08-16 131.072K context $1/M input $1/M output

3 providers

Abacusai: Dracarys Llama 3.1 70B Instruct T

Open weights

Abacus.AI coding fine-tune of Llama 3.1 70B Instruct

abacusai/dracarys-llama-3.1-70b-instruct 2024-08-14 131.072K context Input not listed Output not listed

1 provider

OpenAI: GPT-4o (2024-08-06) T

Tools JSON

GPT model for general reasoning, writing, coding, and tool-assisted tasks

openai/gpt-4o-2024-08-06 2024-08-06 128K context $2.5/M input $10/M output

8 providers

Mistral AI: Mistral Large 2407 T

Tools JSON Open weights

Flagship Mistral model for advanced reasoning, coding, and multilingual work

mistral/mistral-large-2407 2024-07-24 131.072K context $2/M input $6/M output

4 providers

Meta: Llama-Guard-3-8B T

Open weights

Llama 3.1-based safety classifier for moderating prompts and model responses

meta/llama-guard-3-8b 2024-07-23 128K context Input not listed Output not listed

1 provider

Meta: Llama-3.1-8B-Instruct T

Tools JSON Open weights

Compact open Llama model for lightweight chat, drafting, and self-hosting

meta/llama-3.1-8b-instruct 2024-07-23 128K context $0.02/M input $0.04/M output

8 providers

Meta: Llama-3.1-70B-Instruct T

Tools JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

meta/llama-3.1-70b-instruct 2024-07-23 128K context $0.4/M input $0.4/M output

4 providers

OpenAI: GPT-4o mini T

Tools JSON

Small omni GPT for cheap multimodal assistance and production-scale traffic

openai/gpt-4o-mini 2024-07-18 128K context $0.15/M input $0.6/M output

26 providers

Mistral AI: Mistral Nemo T

Tools JSON Open weights

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

mistral/mistral-nemo 2024-07-18 128K context $0.029/M input $0.03/M output

12 providers

Mistral AI: Codestral (latest) T

Tools JSON Open weights

Mistral code model for completions, refactors, and developer IDE workflows

mistral/codestral-latest 2024-05-29 256K context $0.3/M input $0.9/M output

4 providers

Vispark: Vision Large T

Reasoning Tools JSON

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

vispark/vision-large 2024-05-15 1M context $7.37/M input $22.11/M output

1 provider

Vispark: Vision Medium T

Reasoning Tools JSON

Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.

vispark/vision-medium 2024-05-15 1M context $4.21/M input $12.63/M output

1 provider

Vispark: Vision Small T

Reasoning Tools JSON

Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.

vispark/vision-small 2024-05-15 1M context $1.05/M input $3.16/M output

1 provider

OpenAI: GPT-4o (2024-05-13) T

Tools JSON

GPT model for general reasoning, writing, coding, and tool-assisted tasks

openai/gpt-4o-2024-05-13 2024-05-13 128K context $5/M input $15/M output

6 providers

OpenAI: GPT-4o T

Tools JSON

Omni-era GPT for multimodal chat, practical coding, and general assistants

openai/gpt-4o 2024-05-13 128K context $2.5/M input $10/M output

26 providers

Alibaba Qwen: Qwen-VL Max T

Tools

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen-vl-max 2024-04-08 131.072K context $0.8/M input $3.2/M output

5 providers

Anthropic: Claude Haiku 3 T

Legacy model retained for compatibility with older integrations

anthropic/claude-3-haiku-20240307 2024-03-13 200K context Input not listed Output not listed

2 providers

Mistral AI: Mistral Large T

Tools JSON

Flagship Mistral model for advanced reasoning, coding, and multilingual work

mistral/mistral-large 2024-02-26 128K context $2/M input $6/M output

2 providers

Alibaba Qwen: Qwen Plus T

Reasoning Tools

Qwen instruction model for multilingual chat, reasoning, and tool use

alibaba/qwen-plus 2024-01-25 1M context $0.4/M input $1.2/M output

11 providers

Alibaba Qwen: Qwen-VL Plus T

Tools

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen-vl-plus 2024-01-25 131.072K context $0.21/M input $0.63/M output

4 providers

Perplexity: Sonar Reasoning Pro T

Reasoning

Web-grounded Sonar for multi-step research questions that need cited reasoning

perplexity/sonar-reasoning-pro 2024-01-01 128K context $2/M input $8/M output

9 providers

Perplexity: Sonar Pro T

Deeper Sonar search model with broader retrieval and stronger synthesis

perplexity/sonar-pro 2024-01-01 200K context $3/M input $15/M output

10 providers

Perplexity: Sonar T

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

perplexity/sonar 2024-01-01 128K context $1/M input $1/M output

10 providers

OpenAI: GPT-4 Turbo T

Tools

Compact GPT model for low-latency assistance and high-volume workloads

openai/gpt-4-turbo 2023-11-06 128K context $10/M input $30/M output

16 providers

OpenAI: OpenAI: GPT-5.6 Luna Pro T

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

openai/gpt-5.6-luna-pro 1.05M context $0.2/M input $1.2/M output

OpenAI: OpenAI: GPT-5.6 Terra Pro T

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

openai/gpt-5.6-terra-pro 1.05M context $2/M input $12/M output

OpenAI: OpenAI: GPT-5.6 Sol Pro T

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

openai/gpt-5.6-sol-pro 1.05M context $4/M input $20/M output

xAI: SpaceXAI: Grok 4.5 T

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

x-ai/grok-4.5 500K context $2/M input $6/M output

xAI: xAI: Grok Latest T

This model always redirects to the latest Grok model from xAI.

~x-ai/grok-latest 500K context $2/M input $6/M output

Tencent: Tencent: Hy3 (free) T

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

tencent/hy3:free 262.144K context Free input Free output

Poolside: Poolside: Laguna XS 2.1 (free) T

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

poolside/laguna-xs-2.1:free 262.144K context Free input Free output

Nex Agi: Nex AGI: Nex-N2-Mini T

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...

nex-agi/nex-n2-mini 262.144K context $0.025/M input $0.1/M output

Filterable model directory
Model	Creator	Inputs	Context	Input	Output	Released
Claude Haiku 3.5anthropic/claude-3-5-haiku-20241022	Anthropic	T	200K	$0.8	$4	2024-10-22
Claude Sonnet 3.5 v2anthropic/claude-3-5-sonnet-20241022	Anthropic	T	200K	—	—	2024-10-22
Ministral 8B Instructmistral/ministral-8b-instruct-2410	Mistral AI	T	131.072K	—	—	2024-10-16
Ministral 3Bmistral/ministral-3b	Mistral AI	T	128K	$0.04	$0.04	2024-10-16
Palmyra X4writer/palmyra-x4	Writer	T	128K	$2.5	$10	2024-10-09
Llama-3.2-1Bmeta/llama-3.2-1b	Meta	T	131.072K	—	—	2024-09-25
Llama-3.2-3Bmeta/llama-3.2-3b	Meta	T	131.072K	—	—	2024-09-25
Llama-3.2-11B-Vision-Instructmeta/llama-3.2-11b-vision-instruct	Meta	T	128K	$0.055	$0.055	2024-09-25
Llama 3.2 1B Instructmeta/llama-3.2-1b-instruct	Meta	T	131.072K	$0.01	$0.01	2024-09-25
Llama-3.2-90B-Vision-Instructmeta/llama-3.2-90b-vision-instruct	Meta	T	128K	—	—	2024-09-25
Llama 3.2 3B Instructmeta/llama-3.2-3b-instruct	Meta	T	131.072K	$0.02	$0.02	2024-09-25
Qwen2.5 7B Instructalibaba/qwen2.5-7b-instruct	Alibaba Qwen	T	131.072K	$0.1	$0.2	2024-09-19
Pixtral 12Bmistral/pixtral-12b	Mistral AI	T	128K	$0.15	$0.15	2024-09-11
Command Rcohere/command-r-08-2024	Cohere	T	128K	$0.15	$0.6	2024-08-30
Command R+cohere/command-r-plus-08-2024	Cohere	T	128K	$2.5	$10	2024-08-30
Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b	Sao10K	T	131.072K	$0.85	$0.85	2024-08-28
Nemotron Mini 4B Instructnvidia/nemotron-mini-4b-instruct	NVIDIA	T	128K	—	—	2024-08-21
Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b	Nousresearch	T	131.072K	$0.7	$0.7	2024-08-18
Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b	Nousresearch	T	131.072K	$1	$1	2024-08-16
Dracarys Llama 3.1 70B Instructabacusai/dracarys-llama-3.1-70b-instruct	Abacusai	T	131.072K	—	—	2024-08-14
GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06	OpenAI	T	128K	$2.5	$10	2024-08-06
Mistral Large 2407mistral/mistral-large-2407	Mistral AI	T	131.072K	$2	$6	2024-07-24
Llama-Guard-3-8Bmeta/llama-guard-3-8b	Meta	T	128K	—	—	2024-07-23
Llama-3.1-8B-Instructmeta/llama-3.1-8b-instruct	Meta	T	128K	$0.02	$0.04	2024-07-23
Llama-3.1-70B-Instructmeta/llama-3.1-70b-instruct	Meta	T	128K	$0.4	$0.4	2024-07-23
GPT-4o miniopenai/gpt-4o-mini	OpenAI	T	128K	$0.15	$0.6	2024-07-18
Mistral Nemomistral/mistral-nemo	Mistral AI	T	128K	$0.029	$0.03	2024-07-18
Codestral (latest)mistral/codestral-latest	Mistral AI	T	256K	$0.3	$0.9	2024-05-29
Vision Largevispark/vision-large	Vispark	T	1M	$7.37	$22.11	2024-05-15
Vision Mediumvispark/vision-medium	Vispark	T	1M	$4.21	$12.63	2024-05-15
Vision Smallvispark/vision-small	Vispark	T	1M	$1.05	$3.16	2024-05-15
GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13	OpenAI	T	128K	$5	$15	2024-05-13
GPT-4oopenai/gpt-4o	OpenAI	T	128K	$2.5	$10	2024-05-13
Qwen-VL Maxalibaba/qwen-vl-max	Alibaba Qwen	T	131.072K	$0.8	$3.2	2024-04-08
Claude Haiku 3anthropic/claude-3-haiku-20240307	Anthropic	T	200K	—	—	2024-03-13
Mistral Largemistral/mistral-large	Mistral AI	T	128K	$2	$6	2024-02-26
Qwen Plusalibaba/qwen-plus	Alibaba Qwen	T	1M	$0.4	$1.2	2024-01-25
Qwen-VL Plusalibaba/qwen-vl-plus	Alibaba Qwen	T	131.072K	$0.21	$0.63	2024-01-25
Sonar Reasoning Properplexity/sonar-reasoning-pro	Perplexity	T	128K	$2	$8	2024-01-01
Sonar Properplexity/sonar-pro	Perplexity	T	200K	$3	$15	2024-01-01
Sonarperplexity/sonar	Perplexity	T	128K	$1	$1	2024-01-01
GPT-4 Turboopenai/gpt-4-turbo	OpenAI	T	128K	$10	$30	2023-11-06
OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro	OpenAI	T	1.05M	$0.2	$1.2	—
OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-pro	OpenAI	T	1.05M	$2	$12	—
OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-pro	OpenAI	T	1.05M	$4	$20	—
SpaceXAI: Grok 4.5x-ai/grok-4.5	xAI	T	500K	$2	$6	—
xAI: Grok Latest~x-ai/grok-latest	xAI	T	500K	$2	$6	—
Tencent: Hy3 (free)tencent/hy3:free	Tencent	T	262.144K	Free	Free	—
Poolside: Laguna XS 2.1 (free)poolside/laguna-xs-2.1:free	Poolside	T	262.144K	Free	Free	—
Nex AGI: Nex-N2-Mininex-agi/nex-n2-mini	Nex Agi	T	262.144K	$0.025	$0.1	—