Sponsored byFusecodeEnterprise coding API for Claude Code, Codex, and model workflows.
LogoLMSpeed
  • Free
  • Models
  • Providers
  • Docs
LogoLMSpeed
  1. Home
  2. Models
  3. Categories
  4. LLM
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
  • Model Pricing
  • Model Speed
  • 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
Tools
  • Speed Test
  • Provider Audit
Resources
  • Provider Directory
  • Documentation
  • GEO Checker
  • Viora
  • Botab
  • VidBee
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️
All347LLM (Text-to-text)342Image Generation5
Newest342Most tested0Recently tested0A–Z0
Top for reasoning73
  • ClaudeClaude Fable 5
  • GeminiGemini 3 Flash Preview
  • GeminiGemini 3.1 Pro Preview
On this page
Top for coding73.4
  • ClaudeClaude Fable 5
  • GeminiGemini 3 Flash Preview
  • GrokGrok 4.5
On this page
Lowest latency2.217s
  • ClaudeClaude Opus 4.8
  • ClaudeClaude Fable 5
  • ClaudeClaude Opus 4.7
On this page
Highest throughput255 t/s
  • ClaudeClaude Opus 4.8
  • GeminiGemini 3.1 Flash Lite
  • ClaudeClaude Fable 5
On this page
342 Visible models
ModelContextInputOutputThroughputLatencyProvidersAgentsCodingReasoningKnowledgeMathMultilingualMultimodalInstruction following
OpenAIGPT-3.5 Turbo (older v0613)4.1K—————————————
OpenAIGPT-4o (2024-05-13)128K——————32.243.1—45.1———
OpenAIGPT-4o (2024-08-06)128K——————32.427.5—45.6———
MetaAIHermes 3 70B Instruct131.1K——————2133.8—28.1———
MistralMistral Large 2407131.1K——————26.939.6—40.4———
MetaAIR1 Distill Llama 70B128K————
—2941.9—80.2———
OpenAIo3 Mini High200K——————56.656.6—92.2———
OpenAIo4 Mini High200K—————————————
QwenQwen3 235B A22B131.1K——————51.154.8—88.5———
QwenQwen3 32B131.1K——————4551.6—88.4———
QwenQwen3 14B131.7K——————4247.4—86.2———
QwenQwen3 8B131.1K——————31.645.8—82.5———
QwenQwen3 30B A3B131.1K——————39.648.6—85.6———
GeminiGemini 2.5 Pro Preview 06-051.0M——————59.360.4—91.5———
QwenQwen3 235B A22B Instruct 2507262.1K——————60.659.4—96.2———
QwenQwen3 Coder 30B A3B Instruct160K————
—34.142.1—59.5———
OpenAIgpt-oss-20b131.1K—————33.339.33440.6——10065.1
OpenAIgpt-oss-120b131.1K————
37.745.240.346.6——10069
MoonshotAIKimi K2 0905262.1K——————45.955—————
QwenQwen3 Next 80B A3B Instruct262.1K————
+13
—49.654.3—————
QwenQwen3 VL 235B A22B Instruct262.1K————
+1
—47.753.3—————
GeminiGemini 2.5 Flash Lite Preview 09-20251.0M——————46.349.8—————
DeepSeekDeepSeek V3.2 Exp163.8K——————47.755.3—————
QwenQwen3 VL 30B A3B Instruct262.1K————
—39.250.8—————
QwenQwen3 VL 8B Instruct256K————
—25.338.1—————
QwenQwen3 VL 32B Instruct262.1K————
—40.850.8—————
OpenAIOlmo 3 32B Think65.5K——————47.947.6—————
GeminiGemini 3 Flash Preview1.0M————
—70.771.2—————
QwenQwen3.5 397B A17B256K——————41.152.5—————
GeminiGemini 3.1 Pro Preview1.0M————
+2
—58.969.4—————
QwenQwen3.5-122B-A10B262.1K————
58.545.35253.1—82.281.784.6
QwenQwen3.5-27B262.1K—————58.44852.151.3—82.282.185.3
QwenQwen3.5-35B-A3B262.1K—————54.843.350.450.2—8180.682.2
GeminiGemini 3.1 Flash Lite Preview1.0M————
—41.949.2—————
QwenQwen3.5-9B262.1K——————27.743.6—————
NvidiaNemotron 3 Super1M————
+5
————————
HunyuanHy3 preview262.1K————
+1
61.347.842.958———63.1
QwenQwen3.6 27B262.1K————
66.35552.457.788.7—81.667.6
QwenQwen3.6 Max Preview262.1K————
+9
80.15047.846.2———76.6
QwenQwen3.6 35B A3B262.1K————
+1
55.95050.751.387—8064.4
NvidiaNemotron 3 Nano Omni256K————
+8
—27.826.1—————
Granite 4.1 8B131.1K——————21.823.5—————
NvidiaNemotron 3 Ultra1M————
+8
—39.956.7—————
GrokGrok 4.5500K————
+1
83.369.466.7—————
ChatGLMGLM-5.21.0M——61 t/s6.89s
+101
61.55955.546.294.3—10073.3
MoonshotAIKimi K2.7262.1K————
+29
————————
ClaudeClaude Fable 51M——72 t/s2.83s
+88
89.173.4735997.687.373.9—
ClaudeClaude Opus 4.81M——255 t/s2.22s
+121
70.963.556.655.896.787.684.962.2
ClaudeClaude Opus 4.71M——48 t/s3.75s
+168
53.458.650.845.3——88.243.6
GeminiGemini 3.1 Flash Lite1.0M——183 t/s6.98s
+100
32.533.633.248.3——74.477.2
GeminiGemini Pro1.0M————
+31
————————
GeminiGemini Flash1.0M————
+35
————————
QwenQwen3.5 Plus1M——51 t/s13.81s
+101
—15.7——————
DeepSeekDeepSeek V4 Pro1.0M——43 t/s8.37s
+171
57.66662.367.378.4—10076.5
DeepSeekDeepSeek V4 Flash1.0M——69 t/s7.31s
+179
60.463.258.66275.5—10079.2
MiMo-V2.5-TTS-VoiceDesign—————
+32
————————
MiMo-V2.5-TTS-VoiceClone—————
+35
————————
MiMo-V2.5-TTS—————
+35
————————
QwenQwen3 Instant—————
————————
MiMo-V2.5-Pro1.0M——45 t/s5.93s
+92
59.154.949.435.3——10079.9
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6