Open AI Foundation Models Index

AI Foundation Models & LLM Specifications

Cataloged specifications and pricing snapshots per 1M tokens, prompt caching rates, and tool-calling support. Discover which models best power your MCP tools and agent loops.

610

Foundation Models

467

MCP Tool-Call Ready

350

Reasoning & Thinking

317

Open Weights (HuggingFace)

Search models

Sort models

Filter by Capability:

Context:

View all 232 providers →

Showing 505-540 of 610 models

Command R7B Arabic

cohere/command-r7b-arabic-02-2025•Cohere

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

In: $0.04 • Out: $0.15

Phi-4-multimodal-instruct

microsoft/phi-4-multimodal-instruct•Microsoft

Compact Microsoft multimodal model for text, image, and speech understanding

131.1K out maxVision

In: $0.07 • Out: $0.11

microsoft/phi-4-mini•Microsoft

Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks

4.1K out maxMMLU: 67.3 accuracy

In: $0.17 • Out: $0.68

Claude Sonnet 3.7

anthropic/claude-3-7-sonnet-20250219•Anthropic

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

64K out maxVisionPDFAider Polyglot: 64.9 percent correct

In: $3.00 • Out: $15.00

mistral/mistral-saba•Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

26.2K out maxPDF

In: $0.20 • Out: $0.59

MiniMax image-01

minimax/image-01•MiniMax

MiniMax text-to-image generation model with reference-image support

4.1K out maxVision

In: Free • Out: Free

Aion-RP 1.0 (8B)

aion-labs/aion-rp-llama-3.1-8b•Aion-labs

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

In: $0.80 • Out: $1.60

Sonar Deep Research

perplexity/sonar-deep-research•Perplexity

Sonar search model for autonomous research and citation-backed long-form reports

In: $2.00 • Out: $8.00

Mistral Small 3

mistral/mistral-small-24b-instruct-2501•Mistral

Efficient Mistral model for fast chat, extraction, and production assistants

In: $0.12 • Out: $0.35

Qwen2.5-VL 72B Instruct

alibaba/qwen2-5-vl-72b-instruct•Alibaba

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

8.2K out maxVision

In: $2.80 • Out: $8.40

sdaia/allam-2-7b•Sdaia

ALLaM-2-7b instruction tuned model by SDAIA

In: Free • Out: Free

DeepSeek-R1-Distill-Qwen-32B

deepseek/deepseek-r1-distill-qwen-32b•DeepSeek

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

In: $0.29 • Out: $0.86

deepseek/deepseek-r1•DeepSeek

Classic open reasoning model for transparent math, coding, and deliberate problem solving

32.8K out maxAider Polyglot: 56.9 percent correct

In: $0.70 • Out: $2.50

Qwen-Omni Turbo

alibaba/qwen-omni-turbo•Alibaba

Qwen omni model for text, vision, audio, and multimodal agent tasks

2K out maxVision

In: $0.07 • Out: $0.27

MiniMax Text 01 (MiniMax)

minimax/MiniMax-Text-01•MiniMax

MiniMax model for chat, coding, office work, and agentic tasks

In: $0.20 • Out: $1.10

deepseek/deepseek-v3•DeepSeek

Open DeepSeek MoE chat model for coding, math, and general reasoning

In: $0.50 • Out: $1.50

openai/o3-mini•OpenAI

Smaller o-series reasoner for economical coding, math, and planning tasks

100K out maxAider Polyglot: 60.4 percent correct

In: $1.10 • Out: $4.40

Llama 3.3 Euryale 70B

sao10k/l3.3-euryale-70b•Sao10k

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

In: $0.89 • Out: $1.03

cohere/command-r7b-12-2024•Cohere

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

In: $0.04 • Out: $0.15

Gemini 2.0 Flash

google/gemini-2.0-flash•Google

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

8.2K out maxVisionPDF

In: $0.07 • Out: $0.30

Gemini 2.0 Flash-Lite

google/gemini-2.0-flash-lite•Google

Low-latency Gemini model for high-volume multimodal and agent workloads

8.2K out maxVisionPDF

In: $0.07 • Out: $0.30

Llama-3.3-70B-Instruct

meta/llama-3.3-70b-instruct•Meta

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

4.1K out maxArtificial Analysis Coding Index: 10.7 index

In: $0.72 • Out: $0.72

amazon/nova-lite-v1•Amazon Bedrock

Efficient model for low-latency assistance, extraction, and routine automation

5.1K out maxVision

In: $0.07 • Out: $0.28

amazon/nova-pro-v1•Amazon Bedrock

Flagship model for demanding analysis, coding, and production agent workflows

5.1K out maxVision

In: $0.92 • Out: $3.67

openai/o1•OpenAI

O-series reasoning model for hard analysis, math, coding, and planning

100K out maxVisionPDFAider Polyglot: 61.7 percent correct

In: $15.00 • Out: $60.00

amazon/nova-micro-v1•Amazon Bedrock

Efficient model for low-latency assistance, extraction, and routine automation

In: $0.04 • Out: $0.16

amazon/nova-lite•Amazon Bedrock

Efficient model for low-latency assistance, extraction, and routine automation

10K out maxVisionPDF

In: $0.07 • Out: $0.28

amazon/nova-pro•Amazon Bedrock

Flagship model for demanding analysis, coding, and production agent workflows

10K out maxVisionPDF

In: $0.92 • Out: $3.67

amazon/nova-micro•Amazon Bedrock

Efficient model for low-latency assistance, extraction, and routine automation

In: $0.04 • Out: $0.16

GPT-4o (2024-11-20)

openai/gpt-4o-2024-11-20•OpenAI

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

16.4K out maxVisionAider Polyglot: 18.2 percent correct

In: $2.50 • Out: $10.00

Mistral Large 2.1

mistral/mistral-large-2411•Mistral

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

16.4K out maxArtificial Analysis Coding Index: 13.8 index

In: $2.00 • Out: $6.00

Qwen2.5-Coder-32B-Instruct

alibaba/qwen2.5-coder-32b-instruct•Alibaba

Open coding-focused Qwen model for code generation, repair, and repository reasoning

In: $0.20 • Out: $0.20

Qwen2.5-Coder-0.5B

alibaba/qwen2.5-coder-0.5b•Alibaba

Tiny open Qwen code model for lightweight completion and on-device coding

In: $0.10 • Out: $0.10

thedrummer/unslopnemo-12b•Thedrummer

Open-weight instruction model for adaptable chat and self-hosted production workloads

In: $0.55 • Out: $0.55

alibaba/qwen-turbo•Alibaba

Efficient Qwen model for fast chat, extraction, and high-volume workloads

In: $0.05 • Out: $0.20

Mistral Large (latest)

mistral/mistral-large-latest•Mistral

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

262.1K out maxVision

In: $0.50 • Out: $1.50