ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
3,424 models
8K+
Meta: Llama-3.2-11B-Vision-Instruct T
Tools JSON 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
Mistral AI: Pixtral 12B T
Tools Open weights

Mistral vision-language model for image understanding and multimodal chat

mistral/pixtral-12b 2024-09-01 128K context $0.15/M input $0.15/M output
4 providers
Alibaba Qwen: Qwen2.5-VL 72B Instruct T
Tools Open weights

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

alibaba/qwen2-5-vl-72b-instruct 2024-09 131.072K context $2.8/M input $8.4/M output
3 providers
Cohere: Command R+ T
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
9 providers
Cohere: Command R T
Tools JSON 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
7 providers
NVIDIA: Nemotron Mini 4B Instruct T
Tools 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
OpenAI: GPT-4o (2024-08-06) T
Tools

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
7 providers
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
7 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-3.1-70B-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

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
23 providers
Mistral AI: Mistral Nemo T
Open weights

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

mistral/mistral-nemo 2024-07-01 128K context $0.15/M input $0.15/M output
11 providers
OpenAI: o3-deep-research T
Reasoning Tools

Research model for long-horizon investigation, synthesis, and analytical reports

openai/o3-deep-research 2024-06-26 200K context $9/M input $36/M output
6 providers
OpenAI: o4-mini-deep-research T
Reasoning Tools

Research model for long-horizon investigation, synthesis, and analytical reports

openai/o4-mini-deep-research 2024-06-26 200K context $1.8/M input $7.2/M output
5 providers
Mistral AI: Codestral (latest) T
Tools 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
5 providers
Mistral AI: Codestral-22B-v0.1 T
Open weights

Open Mistral code model for fill-in-the-middle and 80+ programming languages

mistral/codestral-22b-v0.1 2024-05-29 32.768K context $0.3/M input $0.9/M output
1 provider
OpenAI: GPT-4o T
Tools

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
23 providers
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
5 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
Alibaba Qwen: Qwen Max T
Tools

Flagship Qwen model for complex reasoning, coding, and agentic workflows

alibaba/qwen-max 2024-04-03 32.768K context $1.6/M input $6.4/M output
6 providers
Anthropic: Claude Haiku 3 T
Tools

Legacy model retained for compatibility with older integrations

anthropic/claude-3-haiku-20240307 2024-03-13 200K context $0.25/M input $1.25/M output
2 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
Alibaba Qwen: Qwen Plus T
Reasoning

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
10 providers
Perplexity: Sonar Reasoning Pro T
JSON

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
JSON

Deeper Sonar search model with broader retrieval and stronger synthesis

perplexity/sonar-pro 2024-01-01 200K context $3/M input $15/M output
9 providers
Perplexity: Sonar T
JSON

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

perplexity/sonar 2024-01-01 128K context $1/M input $1/M output
9 providers
OpenAI: GPT-4 T
Tools

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

openai/gpt-4 2023-11-06 8.192K context $30/M input $60/M output
11 providers
OpenAI: GPT-4 Turbo T

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
15 providers
OpenAI: GPT-3.5-turbo T

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

openai/gpt-3.5-turbo 2023-03-01 16.385K context $0.5/M input $1.5/M output
13 providers
Liquid: LiquidAI: LFM2.5-1.2B-Thinking (free) T

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

liquid/lfm-2.5-1.2b-thinking:free 32.768K context Free input Free output
Google: Google: Gemini Pro Latest T

This model always redirects to the latest model in the Gemini Pro family.

~google/gemini-pro-latest 1.04858M context $2/M input $12/M output
Relace: Relace: Relace Search T

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

relace/relace-search 256K context $1/M input $3/M output
OpenAI: OpenAI: GPT Mini Latest T

This model always redirects to the latest model in the GPT Mini family.

~openai/gpt-mini-latest 400K context $0.75/M input $4.5/M output
OpenAI: OpenAI: GPT-5.2 Chat T

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

openai/gpt-5.2-chat 128K context $1.75/M input $14/M 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
Cloudflare: @cf/zai-org/glm-5.2 T

No provider description is available for this model yet.

cloudflare/@cf/zai-org/glm-5.2 262.144K context $1.4/M input $4.4/M output
Z Ai: Z.ai: GLM 4.7 T

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

z-ai/glm-4.7 202.752K context $0.4/M input $1.75/M output