AI Models

Open multilingual model optimized for generation across 23 languages

128,000 ctx

Aya Expanse 8B

Compact open multilingual model optimized for generation across 23 languages

8,000 ctx

Aya Vision 32B

Open multilingual vision model for OCR, visual reasoning, and image question answering

16,000 ctx

Aya Vision 8B

Compact open multilingual vision model for OCR and visual question answering

16,000 ctx

Claude Fable 5

1,000,000 ctxclaude-fableKnowledge: 2026-01-31

Claude model for creative writing, analysis, and controlled agent workflows

200,000 ctxclaude-haikuKnowledge: 2023-08-31

Claude Haiku 3

anthropic

Legacy model retained for compatibility with older integrations

200,000 ctxclaude-haikuKnowledge: 2024-07-31

Claude Haiku 3.5

anthropic

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

Claude Haiku 4.5

200,000 ctxclaude-haikuKnowledge: 2025-02-28

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

Claude Haiku 4.5 (latest)

200,000 ctxclaude-haikuKnowledge: 2025-02-28

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Claude Opus 4

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

Claude Opus 4 (latest)

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

Claude Opus 4.1

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

Claude Opus 4.1 (latest)

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

Claude Opus 4.5

200,000 ctxclaude-opusKnowledge: 2025-05

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

Claude Opus 4.5 (latest)

200,000 ctxclaude-opusKnowledge: 2025-05

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

Claude Opus 4.6

1,000,000 ctxclaude-opusKnowledge: 2025-05-31

High-end Claude for difficult coding, planning, and slower expert reasoning

Claude Opus 4.7

1,000,000 ctxclaude-opusKnowledge: 2026-01-31

Stronger Opus tier for advanced software work and high-stakes reasoning

Claude Opus 4.8

1,000,000 ctxclaude-opusKnowledge: 2026-01

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Claude Opus 5

1,000,000 ctxclaude-opusKnowledge: 2026-05

Strongest Claude Opus model for coding, agents, and professional work

200,000 ctxclaude-sonnetKnowledge: 2024-04-30

Claude Sonnet 3.5 v2

anthropic

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

Claude Sonnet 3.7

200,000 ctxclaude-sonnetKnowledge: 2024-10-31

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

Claude Sonnet 4

200,000 ctxclaude-sonnetKnowledge: 2025-03-31

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

Claude Sonnet 4 (latest)

200,000 ctxclaude-sonnetKnowledge: 2025-03-31

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

Claude Sonnet 4.5

200,000 ctxclaude-sonnetKnowledge: 2025-07-31

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

Claude Sonnet 4.5 (latest)

200,000 ctxclaude-sonnetKnowledge: 2025-07-31

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

Claude Sonnet 4.6

1,000,000 ctxclaude-sonnetKnowledge: 2025-08-31

Claude workhorse for coding agents, careful analysis, and production cost control

Claude Sonnet 5

1,000,000 ctxclaude-sonnetKnowledge: 2026-01-31

Everyday Claude agent model for coding, planning, browsing, and general work

Codestral (latest)

256,000 ctxcodestralKnowledge: 2024-10

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

Command A

256,000 ctxcommand-aKnowledge: 2024-06-01

Cohere command model for multilingual enterprise agents, tools, and chat

128,000 ctxcommand-aKnowledge: 2025-04-01

Command A Plus

coherereasoningopen

Cohere's stronger command model for multilingual agents and enterprise workflows

256,000 ctxcommand-aKnowledge: 2024-06-01

Command A Reasoning

coherereasoningopen

Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows

Command A Translate

8,000 ctxcommand-aKnowledge: 2024-06-01

Translation model for multilingual conversion, localization, and cross-language workflows

Command A Vision

128,000 ctxcommand-aKnowledge: 2024-06-01

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

Command R

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

Command R+

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

Command R7B

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

Command R7B Arabic

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

Deep Research Max Preview

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

1,000,000 ctxdeepseekKnowledge: 2025-09

DeepSeek Chat

deepseekopen

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek Reasoner

1,000,000 ctxdeepseek-thinkingKnowledge: 2025-09

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek V4 Flash

1,000,000 ctxdeepseek-flashKnowledge: 2025-05

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

DeepSeek V4 Pro

1,000,000 ctxdeepseek-thinkingKnowledge: 2025-05

Open MoE flagship with million-token context for coding and long agent runs

DeepSeek-R1

128,000 ctxdeepseek-thinkingKnowledge: 2024-07

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

Devstral 2

262,144 ctxdevstralKnowledge: 2025-12

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

Devstral 2 (latest)

262,144 ctxdevstralKnowledge: 2025-12

Mistral coding agent model for repository tasks and software engineering workflows

128,000 ctxdevstralKnowledge: 2025-05

Devstral Medium

mistral

Mistral coding agent model for repository tasks and software engineering workflows

Devstral Small

128,000 ctxdevstralKnowledge: 2025-05

Mistral coding agent model for repository tasks and software engineering workflows

Fugu

sakanareasoning

Multi-agent model for routing expert agents across complex analytical tasks

1,000,000 ctxfugu

Fugu Ultra

sakanareasoning

Quality-first multi-agent model for hard research, analysis, and competitions

1,000,000 ctxfugu

Gemini 2.0 Flash

1,048,576 ctxgemini-flashKnowledge: 2024-06

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

Gemini 2.0 Flash-Lite

1,048,576 ctxgemini-flash-liteKnowledge: 2024-06

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

Gemini 2.5 Computer Use Preview

128,000 ctxgemini-proKnowledge: 2025-01

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

Gemini 2.5 Flash

Fast Gemini workhorse for multimodal apps where latency and price matter

Gemini 2.5 Flash TTS

32,768 ctxgemini-flashKnowledge: 2025-01

Speech generation model for controllable voice, narration, and audio delivery

Gemini 2.5 Flash-Lite

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Gemini 2.5 Pro

Google's proven reasoning model for coding, math, and multimodal analysis

Gemini 2.5 Pro TTS

32,768 ctxgemini-proKnowledge: 2025-01

Speech generation model for controllable voice, narration, and audio delivery

Gemini 3 Flash Preview

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Gemini 3 Pro Preview

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Gemini 3.1 Flash Lite

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

Gemini 3.1 Flash Lite Preview

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

Gemini 3.1 Flash Live Preview

131,072 ctxgemini-flashKnowledge: 2025-01

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

Gemini 3.1 Flash TTS Preview

8,192 ctxgemini-flashKnowledge: 2025-01

Low-latency speech generation with steerable prompts and expressive audio tags

Gemini 3.1 Pro Preview

Reasoning-first Gemini preview for agentic coding and complex problem solving

Gemini 3.1 Pro Preview Custom Tools

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Gemini 3.5 Flash

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini 3.5 Flash Lite

1,048,576 ctxgemini-flash-liteKnowledge: 2026-03

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini 3.5 Live Translate Preview

131,072 ctxgemini-proKnowledge: 2025-01

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

Gemini 3.6 Flash

1,048,576 ctxgemini-flashKnowledge: 2026-03

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini Deep Research Preview

Agentic model for autonomous multi-step research, synthesis, and cited reports

Gemini Embedding 001

2,048 ctxgeminiKnowledge: 2025-05

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Gemini Embedding 2

8,192 ctxgeminiKnowledge: 2025-11

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

Gemini Flash Latest

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini Flash-Lite Latest

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

Gemini Omni Flash Preview

Video generation and editing model for fast, conversational text- and image-to-video workflows

1,048,576 ctxgemini

Gemini Robotics-ER 1.6 Preview

131,072 ctxgeminiKnowledge: 2025-01

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics

Gemma 4 26B A4B IT

Open Gemma instruction model for efficient chat and self-hosted deployments

262,144 ctxgemma

Gemma 4 31B IT

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

262,144 ctxgemma

Gemma 4 E2B IT

Open Gemma instruction model for efficient chat and self-hosted deployments

131,072 ctxgemma

Gemma 4 E4B IT

Open Gemma instruction model for efficient chat and self-hosted deployments

131,072 ctxgemma

GLM-4.5

131,072 ctxglmKnowledge: 2025-04

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

GLM-4.5-Air

131,072 ctxglm-airKnowledge: 2025-04

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

131,072 ctxglm-flashKnowledge: 2025-04

GLM-4.5-Flash

zhipuaireasoning

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

GLM-4.5V

64,000 ctxglmKnowledge: 2025-04

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

GLM-4.6

204,800 ctxglmKnowledge: 2025-04

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

GLM-4.6V

128,000 ctxglmKnowledge: 2025-04

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

GLM-4.7

204,800 ctxglmKnowledge: 2025-04

Mature GLM model for dependable coding, reasoning, and structured agent tasks

GLM-4.7-Flash

200,000 ctxglm-flashKnowledge: 2025-04

Budget GLM lane for fast coding help, routing, and everyday automation

GLM-4.7-FlashX

200,000 ctxglm-flashKnowledge: 2025-04

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

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

204,800 ctxglm

GLM-5-Turbo

zhipuaireasoning

Faster GLM-5 lane for coding agents that need lower latency

200,000 ctxglm

GLM-5.1

Strong GLM coding model for agentic engineering, terminals, and repository generation

200,000 ctxglm

GLM-5.2

Open flagship GLM for long-horizon coding agents and million-token context work

1,000,000 ctxglm

GLM-5V-Turbo

zhipuaireasoning

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

200,000 ctxglm

GPT OSS 120B

openaireasoningopen

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

131,072 ctxgpt-oss

GPT OSS 20B

openaireasoningopen

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

131,072 ctxgpt-oss

GPT OSS Safeguard 120B

openaireasoningopen

Safety model for policy screening, moderation, and risk-aware routing workflows

131,072 ctxgpt-oss

GPT Realtime Whisper

Streaming speech-to-text model for low-latency transcript deltas from live audio

0whisper

GPT-3.5-turbo

16,385 ctxgptKnowledge: 2021-09-01

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

100

GPT-4

8,192 ctxgptKnowledge: 2023-11

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

101

GPT-4 Turbo

128,000 ctxgptKnowledge: 2023-12

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

102

GPT-4.1

1,047,576 ctxgptKnowledge: 2024-04

Long-lived GPT workhorse for coding, instruction following, and production apps

103

GPT-4.1 mini

1,047,576 ctxgpt-miniKnowledge: 2024-04

Affordable GPT-4.1 lane for fast coding help and structured extraction

104

GPT-4.1 nano

1,047,576 ctxgpt-nanoKnowledge: 2024-04

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

105

GPT-4o

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

106

GPT-4o (2024-05-13)

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

107

GPT-4o (2024-08-06)

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

108

GPT-4o (2024-11-20)

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

109

GPT-4o mini

128,000 ctxgpt-miniKnowledge: 2023-09

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

110

GPT-5

400,000 ctxgptKnowledge: 2024-09-30

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

111

GPT-5 Chat (latest)

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

112

GPT-5 Mini

400,000 ctxgpt-miniKnowledge: 2024-05-30

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

113

GPT-5 Nano

400,000 ctxgpt-nanoKnowledge: 2024-05-30

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

114

GPT-5 Pro

400,000 ctxgpt-proKnowledge: 2024-09-30

Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning

115

GPT-5-Codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

116

GPT-5.1

400,000 ctxgptKnowledge: 2024-09-30

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

117

GPT-5.1 Chat

128,000 ctxgpt-codexKnowledge: 2024-09-30

Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations

118

GPT-5.1 Codex

Codex GPT for repository edits, code review, and practical software agents

119

GPT-5.1 Codex Max

Coding-optimized GPT model for repository edits, reviews, and agentic software work

120

GPT-5.1 Codex mini

Coding-optimized GPT model for repository edits, reviews, and agentic software work

121

GPT-5.2

400,000 ctxgptKnowledge: 2025-08-31

Reliable GPT generation for broad coding, writing, and tool-assisted product work

122

GPT-5.2 Chat

128,000 ctxgpt-codexKnowledge: 2025-08-31

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

123

GPT-5.2 Codex

400,000 ctxgpt-codexKnowledge: 2025-08-31

Code-specialist GPT for repository edits, reviews, and long-running software agents

124

GPT-5.2 Pro

400,000 ctxgpt-proKnowledge: 2025-08-31

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

125

GPT-5.3 Chat (latest)

128,000 ctxgptKnowledge: 2025-08-31

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

126

GPT-5.3 Codex

400,000 ctxgpt-codexKnowledge: 2025-08-31

Coding-optimized GPT model for repository edits, reviews, and agentic software work

127

GPT-5.4

1,050,000 ctxgptKnowledge: 2025-08-31

Agent-ready GPT for coding and computer-use workflows at a lower cost

128

GPT-5.4 mini

400,000 ctxgpt-miniKnowledge: 2025-08-31

Strong small GPT for coding subagents, quick tool use, and high-volume work

129

GPT-5.4 nano

400,000 ctxgpt-nanoKnowledge: 2025-08-31

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

130

GPT-5.4 Pro

1,050,000 ctxgpt-proKnowledge: 2025-08-31

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

131

GPT-5.5

1,050,000 ctxgptKnowledge: 2025-12-01

Default frontier GPT for coding, computer use, research, and knowledge work

132

GPT-5.5 Instant

400,000 ctxKnowledge: 2025-12-01

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

133

GPT-5.5 Pro

1,050,000 ctxgpt-proKnowledge: 2025-12-01

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

134

GPT-5.6 Luna

1,050,000 ctxgpt-lunaKnowledge: 2026-02-16

Cost-efficient GPT-5.6 model for fast, high-volume workloads

135

GPT-5.6 Sol

1,050,000 ctxgpt-solKnowledge: 2026-02-16

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

136

GPT-5.6 Terra

1,050,000 ctxgpt-terraKnowledge: 2026-02-16

Balanced GPT-5.6 model for capable, cost-efficient everyday work

137

GPT-Image-1

OpenAI image model for production generation, edits, and brand-safe visual workflows

0gpt-image

138

GPT-Image-1.5

Image model for prompt-driven generation, editing, and visual design workflows

0gpt-image

139

GPT-Image-2

Image model for prompt-driven generation, editing, and visual design workflows

0gpt-image

140

GPT-Realtime-2.1

128,000 ctxgptKnowledge: 2024-09-30

Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior

141

Grok 4.20 (Non-Reasoning)

xai

Grok model for agentic tool use, reasoning, coding, and live assistance

1,000,000 ctxgrok

142

Grok 4.20 (Reasoning)

Reasoning Grok for document-heavy analysis and long-horizon tool use

1,000,000 ctxgrok

143

Grok 4.3

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

1,000,000 ctxgrok

144

Grok 4.5

xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk

500,000 ctxgrok

145

Grok Build 0.1

Fast Grok coding model tuned for agentic engineering and iterative edits

256,000 ctxgrok-build

146

Grok Imagine Video 1.5

xai

Video model for image-to-video generation, editing, and extension workflows

1,024 ctxgrok

147

Hy3

tencentreasoningopen

Tencent Hy reasoning model for coding, instruction following, and agent tasks

256,000 ctxHy

148

Hy3 preview

tencentreasoningopen

Tencent Hy reasoning model for coding, instruction following, and agent tasks

256,000 ctxHy

thinkingmachinesreasoningopen

149

Inkling

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

1,048,576 ctxling

150

Kimi K2 Thinking

262,144 ctxkimi-thinkingKnowledge: 2024-08

Thinking Kimi model for slower research passes, planning, and hard technical questions

151

Kimi K2 Thinking Turbo

262,144 ctxkimi-thinkingKnowledge: 2024-08

Kimi reasoning model for long-horizon research, planning, and tool use

152

Kimi K2.5

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

153

Kimi K2.6

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

154

Kimi K2.7 Code

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

155

Kimi K2.7 Code Highspeed

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

156

Kimi K3

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

1,048,576 ctxkimi-k3

157

Laguna M.1

Poolside's open-weight model for agentic coding and long-horizon work

262,144 ctxlaguna

158

Laguna S 2.1

Agentic coding model from Poolside in the XS size class for local deployment

1,048,576 ctxlaguna

159

Laguna XS 2.1

Agentic coding model from Poolside in the XS size class for local deployment

262,144 ctxlaguna

160

Laguna XS.2

Agentic coding model from Poolside in the XS size class for local deployment

262,144 ctxlaguna

161

Llama 3.1 Nemotron 70B Instruct

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

162

Llama 3.1 Nemotron Safety Guard 8B v3

Safety model for policy screening, moderation, and risk-aware routing workflows

163

Llama 3.1 Nemotron Ultra 253B

Flagship Nemotron model for high-throughput reasoning and complex agents

164

Llama 3.3 Nemotron Super 49B v1

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

131,072 ctxnemotron

165

Llama 3.3 Nemotron Super 49B v1.5

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

131,072 ctxnemotron

1,000,000 ctxllamaKnowledge: 2024-08

166

Llama 4 Maverick 17B Instruct

metaopen

Open multimodal Llama for strong reasoning with efficient everyday serving

3,500,000 ctxllamaKnowledge: 2024-08

167

Llama 4 Scout 17B Instruct

metaopen

Open Llama with long-context vision for efficient multimodal agents

168

Llama Nemotron Embed VL 1B v2

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

32,768 ctxnemotron

169

Llama Nemotron Rerank VL 1B v2

Reranking model for improving retrieval quality in search and recommendation systems

128,000 ctxllamaKnowledge: 2023-12

170

Llama-3.3-70B-Instruct

metaopen

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

171

LongCat-2.0

meituanreasoning

Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window

1,000,000 ctxlongcat

172

Lyria 3 Clip Preview

Music generation model for short 30-second clips, loops, and previews from text or image prompts

131,072 ctxlyria

173

Lyria 3 Pro Preview

Music generation model for full-length songs from text or images with vocals and structure

131,072 ctxlyria

128,000 ctxmagistral-mediumKnowledge: 2025-06

174

Magistral Medium (latest)

mistralreasoning

Mistral reasoning model for transparent analysis, math, and complex decisions

256,000 ctxmaiKnowledge: 2025-12

175

MAI-Code-1-Flash

microsoftreasoning

Microsoft coding model built for fast, efficient assistance in everyday developer workflows

176

MiMo-V2-Flash

262,144 ctxmimoKnowledge: 2024-12-01

MiMo flash model for fast multimodal assistance and agent workflows

262,144 ctxmimoKnowledge: 2024-12

177

MiMo-V2-Omni

xiaomireasoning

MiMo omni model for text, image, video, audio, and agents

178

MiMo-V2-Pro

xiaomireasoning

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

179

MiMo-V2.5

Open MiMo model for multimodal coding agents and long-context automation

180

MiMo-V2.5-Pro

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

181

MiMo-V2.5-Pro-UltraSpeed

MiMo pro model for strong multimodal reasoning and agent execution

182

MiniMax-M2

Efficient open MiniMax model built for coding agents and tool-heavy workflows

196,608 ctxminimax

183

MiniMax-M2.1

Earlier MiniMax agent model for practical coding and productivity tasks

184

MiniMax-M2.5

Prior MiniMax coding model for agent workflows, office edits, and automation

185

MiniMax-M2.5-highspeed

High-speed MiniMax model for low-latency coding and agent workflows

186

MiniMax-M2.7

Open MiniMax flagship for coding agents, office automation, and complex environments

187

MiniMax-M2.7-highspeed

Low-latency M2.7 variant for interactive coding plans and agent loops

188

MiniMax-M3

MiniMax multimodal model for long-context coding, perception, and agent planning

512,000 ctxminimax

189

Mistral Large (latest)

262,144 ctxmistral-largeKnowledge: 2024-11

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

190

Mistral Large 2.1

131,072 ctxmistral-largeKnowledge: 2024-11

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

191

Mistral Large 3

262,144 ctxmistral-largeKnowledge: 2024-11

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

192

Mistral Medium (latest)

262,144 ctxmistral-medium

Balanced Mistral model for enterprise assistants, multilingual work, and tools

131,072 ctxmistral-mediumKnowledge: 2025-05

193

Mistral Medium 3

mistral

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

194

Mistral Medium 3.5

262,144 ctxmistral-medium

Balanced Mistral model for enterprise assistants, multilingual work, and tools

195

Mistral Nemo

128,000 ctxmistral-nemoKnowledge: 2024-07

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

196

Mistral Nemotron

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

197

Mistral Small (latest)

256,000 ctxmistral-smallKnowledge: 2025-06

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

198

Mistral Small 3.2

128,000 ctxmistral-smallKnowledge: 2025-03

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

199

Mistral Small 4

256,000 ctxmistral-smallKnowledge: 2025-06

Fast Mistral production model for chat, extraction, and cost-sensitive agents

200

Muse Spark 1.1

metareasoning

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

1,000,000 ctxmuse

201

Nano Banana

32,768 ctxgemini-flashKnowledge: 2024-06

Nano Banana image model for fast generation, edits, and character-consistent assets

202

Nano Banana 2

131,072 ctxgemini-flashKnowledge: 2025-01

Image model for prompt-driven generation, editing, and visual design workflows

203

Nano Banana 2

65,536 ctxgemini-flashKnowledge: 2025-01

Image model for prompt-driven generation, editing, and visual design workflows

204

Nano Banana 2 Lite

65,536 ctxgemini-flash-liteKnowledge: 2025-01

Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing

205

Nano Banana Pro

65,536 ctxgemini-proKnowledge: 2025-01

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

206

Nano Banana Pro

65,536 ctxgemini-proKnowledge: 2025-01

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

207

Nemotron 3 Content Safety

Safety model for policy screening, moderation, and risk-aware routing workflows

208

Nemotron 3 Nano 30B A3B

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

262,144 ctxnemotron

209

Nemotron 3 Nano Omni 30B A3B Reasoning

Open Nemotron omni model combining reasoning with text, vision, and audio

256,000 ctxnemotron

210

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

262,144 ctxnemotron

211

Nemotron 3 Ultra 550B A55B

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

1,000,000 ctxnemotron

212

Nemotron 3.5 Content Safety

Safety model for policy screening, moderation, and risk-aware routing workflows

213

Nemotron Cascade 2 30B A3B

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

256,000 ctxnemotron

214

Nemotron Content Safety Reasoning 4B

Safety model for policy screening, moderation, and risk-aware routing workflows

215

Nemotron Mini 4B Instruct

Compact Nemotron model for efficient reasoning and deployable AI agents

216

Nemotron Nano 12B v2 VL

Nemotron multimodal model for visual reasoning and agentic AI workflows

217

Nemotron Nano 9B v2

Compact Nemotron model for efficient reasoning and deployable AI agents

131,072 ctxnemotron

218

Nemotron VoiceChat

Nemotron multimodal model for visual reasoning and agentic AI workflows

256,000 ctxnorthKnowledge: 2025-09-23

219

North Mini Code

coherereasoningopen

Cohere coding model for practical software engineering and agentic edits

220

o1

200,000 ctxoKnowledge: 2023-09

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

221

o1-pro

200,000 ctxo-proKnowledge: 2023-09

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

222

o3

200,000 ctxoKnowledge: 2024-05

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

223

o3-deep-research

200,000 ctxoKnowledge: 2024-05

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

224

o3-mini

200,000 ctxo-miniKnowledge: 2024-05

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

225

o3-pro

200,000 ctxo-proKnowledge: 2024-05

High-effort o3 tier for difficult technical reasoning and careful answers

226

o4-mini

200,000 ctxo-miniKnowledge: 2024-05

Fast o-series model for compact reasoning, coding, and tool use

227

o4-mini-deep-research

200,000 ctxo-miniKnowledge: 2024-05

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

228

Ornith 1.0 31B

Open coding-reasoning model for repository tasks and self-improving agents

229

Ornith 1.0 35B

Large coding-reasoning model for agentic software tasks and RL search

230

Ornith 1.0 397B

Large coding-reasoning model for agentic software tasks and RL search

231

Ornith 1.0 9B

Open coding-reasoning model for repository tasks and self-improving agents

232

Pixtral 12B

128,000 ctxpixtralKnowledge: 2024-09

Mistral vision-language model for image understanding and multimodal chat

233

Pixtral Large (latest)

128,000 ctxpixtralKnowledge: 2024-11

Mistral's larger vision model for document-heavy image understanding and chat

234

Qwen Flash

1,000,000 ctxqwenKnowledge: 2024-04

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

235

Qwen Max

32,768 ctxqwenKnowledge: 2024-04

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

236

Qwen Plus

1,000,000 ctxqwenKnowledge: 2024-04

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

237

Qwen Turbo

1,000,000 ctxqwenKnowledge: 2024-04

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

238

Qwen-Omni Turbo

32,768 ctxqwenKnowledge: 2024-04

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

239

Qwen-VL Max

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

240

Qwen-VL Plus

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

241

Qwen2.5-VL 72B Instruct

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

242

Qwen3 235B-A22B

Large open Qwen MoE for multilingual reasoning, coding, and tool use

243

Qwen3 32B

Dense open Qwen model for self-hosted chat, reasoning, and coding

244

Qwen3 Coder Flash

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

245

Qwen3 Coder Plus

1,048,576 ctxqwenKnowledge: 2025-04

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

246

Qwen3 Max

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

247

Qwen3-Coder 30B-A3B Instruct

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

248

Qwen3-Coder 480B-A35B Instruct

Open Qwen coding heavyweight for repository reasoning and agentic engineering

249

Qwen3-Next 80B-A3B (Thinking)

Efficient Qwen thinking model for local reasoning, math, and coding agents

250

Qwen3-Next 80B-A3B Instruct

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

251

Qwen3-VL Plus

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

252

Qwen3.5 122B-A10B

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

253

Qwen3.5 27B

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

254

Qwen3.5 35B-A3B

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

255

Qwen3.5 397B-A17B

Large open Qwen multimodal MoE for visual agents and long technical tasks

256

Qwen3.5 9B

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

257

Qwen3.5 Plus

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

258

Qwen3.6 27B

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

259

Qwen3.6 35B-A3B

Open multimodal Qwen MoE for local agents that need vision, audio, and code

260

Qwen3.6 Flash

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

1,000,000 ctxqwen3.6

261

Qwen3.6 Max Preview

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

262

Qwen3.6 Plus

Earlier Qwen multimodal workhorse for million-token agent and document tasks

263

Qwen3.7 Max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

1,000,000 ctxqwen

264

Qwen3.7 Plus

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

265

Qwen3.8 Max Preview

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

1,000,000 ctxqwen

266

QwQ Plus

Qwen reasoning model for deliberate problem solving, math, and coding

267

Sarvam 105B

sarvamreasoningopen

Flagship Indian-language reasoning model for enterprise multilingual applications

131,072 ctxsarvam

268

Sarvam 30B

sarvamreasoningopen

Efficient Indian-language reasoning model for chat, coding, and multilingual work

128,000 ctxsarvam

128,000 ctxsonarKnowledge: 2025-09-01

269

Sonar

perplexity

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

200,000 ctxsonar-proKnowledge: 2025-09-01

270

Sonar Pro

perplexity

Deeper Sonar search model with broader retrieval and stronger synthesis

128,000 ctxsonar-reasoningKnowledge: 2025-09-01

271

Sonar Reasoning Pro

perplexityreasoning

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

256,000 ctxKnowledge: 2025-01

272

Step 3.5 Flash

stepfunreasoningopen

StepFun flash lane for quick multimodal reasoning and coding assistance

256,000 ctxKnowledge: 2025-01

273

Step 3.5 Flash 2603

stepfunreasoningopen

StepFun flash model for efficient multimodal reasoning, coding, and tool use

256,000 ctxKnowledge: 2026-03-01

274

Step 3.7 Flash

stepfunreasoningopen

Newer StepFun flash model for faster agents, coding, and multimodal prompts

275

Veo 3.1 Fast Preview

Video model for prompt-guided generation, editing, and motion workflows

1,024 ctxveo

276

Veo 3.1 Lite Preview

Video model for prompt-guided generation, editing, and motion workflows

1,024 ctxveo

277

Veo 3.1 Preview

Video model for prompt-guided generation, editing, and motion workflows

1,024 ctxveo

278

Whisper 3 Large

openaiopen

Open Whisper checkpoint for robust multilingual transcription and captioning

448 ctxwhisper

279

Whisper Large v3 Turbo

openaiopen

Speech transcription model for accurate audio-to-text and captioning workflows

448 ctxwhisper