LogoLMSpeed
  • Home
  • Free
  • Models
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
  • Input Price
  • Output Price
  • Reasoning
  • Coding
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️

Model Library

Browse canonical models across providers with performance and coverage highlights.

Visible models
301
Active models
301
Providers covered
554
Model variants
29885
Showing 265-288 of 301 models

Phi 4 Mini Instruct

Microsoft Phi 4 Mini Instruct is a compact instruction-tuned variant in the Phi series, optimized for quick responses and high throughput.

Input price+2 free

From $0.010/M

Avg speed

—

First token

—

Providers

25

GeminiGemini 3 Pro

Google Gemini 3 Pro is a high-capability language model in the Gemini series, offering enhanced reasoning, code generation, and multimodal capabilities.

Input price

From $0.0001/M

Avg speed

73 t/s

First token

10.59s

Providers

157

ClaudeClaude Opus 4.6

Anthropic Claude Opus 4.6 is a large language model in the Claude series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+3 free

From $0.0014/M

Avg speed

52 t/s

First token

4.40s

Providers

216

MoonshotAIKimi K2

Moonshot Kimi K2 is a large language model in the Kimi series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+2 free

From $0.0010/M

Avg speed

29 t/s

First token

2.21s

Providers

103

OpenAIO3

OpenAI O3 is a reasoning model in the O series, designed for complex reasoning, problem-solving, and analytical tasks.

Input price

From $0.027/M

Avg speed

134 t/s

First token

2.82s

Providers

86

OpenAIGPT-4.1

OpenAI GPT-4.1 is a language model in the GPT-4 series, offering general-purpose reasoning, code generation, and multimodal capabilities.

Input price

From $0.0010/M

Avg speed

85 t/s

First token

1.92s

Providers

112

OpenAIo1 Mini

OpenAI o1 Mini is a reasoning model in the O series, designed for complex reasoning, problem-solving, and analytical tasks.

Input price

From $0.014/M

Avg speed

32 t/s

First token

13.84s

Providers

70

OpenAIO1

OpenAI O1 is a reasoning model in the O series, designed for complex reasoning, problem-solving, and analytical tasks.

Input price

From $0.027/M

Avg speed

—

First token

—

Providers

80

GeminiGemini 2.5 Pro

Google Gemini 2.5 Pro is a large language model in the Gemini series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+1 free

From $0.0006/M

Avg speed

88 t/s

First token

16.94s

Providers

195

ChatGLMGLM-4.6V

Zhipu AI GLM-4.6V is a multimodal vision-language model in the GLM series, supporting both text and image understanding.

Input price+1 free

From $0.010/M

Avg speed

40 t/s

First token

27.37s

Providers

58

OpenAIGPT-5.1

OpenAI GPT-5.1 is a large language model in the GPT-5 series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+1 free

From $0.0027/M

Avg speed

142 t/s

First token

2.78s

Providers

173

ClaudeClaude Sonnet 4.5

Anthropic Claude Sonnet 4.5 is a language model in the Claude series, offering general-purpose reasoning, code generation, and multimodal capabilities.

Input price+2 free

From $0.0004/M

Avg speed

40 t/s

First token

4.71s

Providers

176

OpenAIGPT-4o Mini

OpenAI GPT-4o Mini is a compact language model in the GPT-4 series, optimized for low-latency responses and efficient inference.

Input price

From $0.0001/M

Avg speed

84 t/s

First token

4.10s

Providers

131

ChatGLMGLM-5

Zhipu GLM-5 is a large language model in the GLM series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+3 free

From $0.0001/M

Avg speed

45 t/s

First token

22.53s

Providers

194

MinimaxMiniMax Hailuo 2.3

MiniMax Hailuo 2.3 is a large language model in the MiniMax series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price

From $0.185/M

Avg speed

—

First token

—

Providers

14

OpenAIGPT-5.4 Mini

OpenAI GPT-5.4 Mini is a compact language model in the GPT-5 series, optimized for quick responses and high throughput.

Input price+4 free

From $0.0002/M

Avg speed

135 t/s

First token

3.86s

Providers

214

MinimaxMiniMax M2.5

MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.

Input price+6 free

From $0.0007/M

Avg speed

57 t/s

First token

9.85s

Providers

193

OpenAIGPT-4o

OpenAI GPT-4o is a multimodal language model in the GPT-4 series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price

From $0.0005/M

Avg speed

82 t/s

First token

3.44s

Providers

134

OpenAIGPT-OSS

GPT-OSS is an open-source language model offering advanced reasoning, code generation, and multimodal capabilities.

Input price+6 free

From $0.0010/M

Avg speed

343 t/s

First token

2.46s

Providers

155

ChatGLMGLM-4

Zhipu GLM-4 is a large language model in the GLM series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price+1 free

From $0.012/M

Avg speed

63 t/s

First token

0.72s

Providers

56

DeepSeekDeepSeek VL2

DeepSeek VL2 is a vision-language model in the DeepSeek series, optimized for multimodal understanding, visual reasoning, and image-text tasks.

Input price

From $0.021/M

Avg speed

126 t/s

First token

0.75s

Providers

14

MAI-DS-R1

A reasoning model by Microsoft in the MAI series, designed for complex reasoning and problem-solving tasks.

Input price

From $0.054/M

Avg speed

—

First token

—

Providers

11

MinimaxMiniMax 01

A language model by MiniMax, offering general-purpose reasoning and multimodal capabilities.

Input price

From $0.029/M

Avg speed

—

First token

—

Providers

9

MinimaxMiniMax M1

MiniMax M1 is a large language model in the MiniMax series, offering advanced reasoning, code generation, and multimodal capabilities.

Input price

From $0.019/M

Avg speed

—

First token

—

Providers

30

  • 1
  • 2
  • 11
  • 12
  • 13
+15 more
+109 more
May 24
+157 more
May 24
+72 more
Apr 8
+62 more
Jul 3
+82 more
Mar 17
+46 more
Jul 21
+55 more
+136 more
Mar 16
+43 more
Apr 29
+122 more
Apr 12
+120 more
Apr 18
+91 more
May 15
+140 more
May 26
+7 more
+158 more
May 23
+141 more
May 14
+101 more
Mar 17
+104 more
Jun 2
+37 more
Apr 10
+4 more
Apr 13
+3 more
+1 more
+19 more