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 397-432 of 610 models

Baichuan M2 32B

baichuan/baichuan-m2-32b•Baichuan

Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes

In: $0.07 • Out: $0.07

Mistral Medium 3.1

mistral/mistral-medium-3.1•Mistral

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

104.9K out maxVisionPDF

In: $0.40 • Out: $2.00

zhipuai/glm-4.5v•Zhipu AI

GLM vision model for visual reasoning, documents, and multimodal agents

16.4K out maxVisionArtificial Analysis Coding Index: 10.9 index

In: $0.30 • Out: $0.90

openai/gpt-5•OpenAI

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

128K out maxVisionAider Polyglot: 88 percent correct

In: $1.25 • Out: $10.00

GPT-5 Chat (latest)

openai/gpt-5-chat-latest•OpenAI

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

128K out maxVision

In: $1.25 • Out: $10.00

openai/gpt-5-mini•OpenAI

Small GPT-5 for responsive agents, coding help, and everyday automation

128K out maxVision

In: $0.25 • Out: $2.00

openai/gpt-5-nano•OpenAI

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

128K out maxVision

In: $0.05 • Out: $0.40

Claude Opus 4.1

anthropic/claude-opus-4-1-20250805•Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDF

In: $15.00 • Out: $75.00

Claude Opus 4.1 (latest)

anthropic/claude-opus-4-1•Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDF

In: $15.00 • Out: $75.00

openai/gpt-oss-120b•OpenAI

Open GPT reasoning model for self-hosted agents and controllable deployments

In: $0.09 • Out: $0.45

openai/gpt-oss-20b•OpenAI

Open GPT reasoning model for self-hosted agents and controllable deployments

In: $0.04 • Out: $0.17

Qwen3-Coder 30B-A3B Instruct

alibaba/qwen3-coder-30b-a3b-instruct•Alibaba

Smaller Qwen coder for efficient local agents and repo-level fixes

65.5K out maxArtificial Analysis Coding Index: 19.4 index

In: $0.45 • Out: $2.25

Command A Vision

cohere/command-a-vision-07-2025•Cohere

Cohere vision model for multilingual document analysis, OCR, and image understanding

8K out maxVision

In: $2.50 • Out: $10.00

Codestral 25.08

mistral/codestral-2508•Mistral

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

In: $0.30 • Out: $0.90

alibaba/qwen-flash•Alibaba

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

In: $0.05 • Out: $0.40

Qwen3 Coder Flash

alibaba/qwen3-coder-flash•Alibaba

Qwen coding model for software agents, repository edits, and code reasoning

In: $0.30 • Out: $1.50

Qwen3 30B-A3B Instruct 2507

alibaba/qwen3-30b-a3b-instruct-2507•Alibaba

Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use

In: $0.10 • Out: $0.30

zhipuai/glm-4.5•Zhipu AI

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

98.3K out maxArtificial Analysis Coding Index: 26.3 index

In: $0.60 • Out: $2.20

zhipuai/glm-4.5-air•Zhipu AI

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

98.3K out maxArtificial Analysis Coding Index: 23.8 index

In: $0.12 • Out: $0.90

zhipuai/glm-4.5-flash•Zhipu AI

Efficient GLM model for fast reasoning, coding, and agent workflows

In: Free • Out: Free

Qwen3 235B-A22B Thinking 2507

alibaba/qwen3-235b-a22b-thinking-2507•Alibaba

Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use

In: $0.30 • Out: $0.50

Llama 3.3 Nemotron Super 49B v1.5

nvidia/llama-3.3-nemotron-super-49b-v1.5•NVIDIA

Nemotron model for efficient reasoning, coding, and specialized AI agents

In: $0.40 • Out: $0.40

alibaba/qwen-mt-plus•Alibaba

Flagship Qwen translation model with terminology control and support for 92 languages

In: $2.46 • Out: $7.37

Qwen3 Coder Plus

alibaba/qwen3-coder-plus•Alibaba

Hosted Qwen coder for software agents, repo edits, and long-context code

In: $1.00 • Out: $5.00

Qwen3-Coder 480B-A35B Instruct

alibaba/qwen3-coder-480b-a35b-instruct•Alibaba

Open Qwen coding heavyweight for repository reasoning and agentic engineering

65.5K out maxSWE-Bench Pro: 38.7 resolve rate

In: $1.50 • Out: $7.50

Qwen3 235B-A22B Instruct 2507

alibaba/qwen3-235b-a22b-instruct-2507•Alibaba

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

In: $0.20 • Out: $0.60

Voxtral Mini 3B 2507

mistral/voxtral-mini-3b-2507•Mistral

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

In: $0.04 • Out: $0.04

Voxtral Small 24B 2507

mistral/voxtral-small-24b-2507•Mistral

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

In: $0.23 • Out: $0.51

Voxtral Small (latest)

mistral/voxtral-small-latest•Mistral

Instruct model with native audio input for speech understanding and tool use

In: $0.10 • Out: $0.40

moonshotai/kimi-k2•Moonshot AI

Kimi model for long-context chat, coding, and agentic reasoning

In: $0.47 • Out: $2.97

Kimi K2 Instruct

moonshotai/kimi-k2-instruct•Moonshot AI

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

In: $0.40 • Out: $1.80

Devstral Medium

mistral/devstral-medium-2507•Mistral

Mistral coding agent model for repository tasks and software engineering workflows

128K out maxSWE-Bench Verified: 61.6 resolved

In: $0.40 • Out: $2.00

mistral/devstral-small-2507•Mistral

Mistral coding agent model for repository tasks and software engineering workflows

128K out maxSWE-Bench Verified: 53.6 resolved

In: $0.10 • Out: $0.30

cognitivecomputations/dolphin-mistral-24b-venice-edition•Cognitivecomputations

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

In: $0.28 • Out: $1.24

Cognitivecomputations

morph/morph-v3-large•Morph

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

In: $0.90 • Out: $1.90

morph/morph-v3-fast•Morph

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

In: $0.80 • Out: $1.20