Top speed

Constituent models

Re-ranks the candidate pool below by measured throughput and latency on every request, trying the fastest model first.

Candidate poolOrder decided per request by measured throughput/latency

Claude Fable 5

GPT-5.2

Llama 4 Maverick

Qwen3 235B

DeepSeek V3.2

GLM-5.2

Llama 4 Scout

GPT-5.1

GPT-5 mini

GPT-5 nano

Claude Sonnet 5

Claude Haiku 4.5

Claude Opus 4.8

Gemini 3 Flash

Gemini 2.5 Flash

Grok 4.5

Grok 4.3

Solar Pro 3

Solar Mini

Kimi K2.6

MiniMax M3

Tencent Hunyuan 3

GPT-5.4

GPT-5.4 mini

GPT-5.4 nano

GPT-5.5

GPT-5.6 Luna

GPT-5.6 Terra

GPT-5.6 Sol

GPT-5.3 Codex

Gemini 3.5 Flash

Gemini 3.1 Pro

Gemini 3.1 Flash Lite

Gemini 2.5 Pro

Grok 4.20

DeepSeek V4 Pro

GLM-5

Qwen3 Max

Qwen3 VL 235B

Kimi K2.7 Code

Kimi K2 Thinking

Nemotron 3 Ultra

Sonar

Sonar Pro

Sonar Reasoning Pro

OLMo 3.1 32B Instruct

OLMoCR 2

OLMoCR 2 7B 1025

OLMoCR 7B 0725 FP8

OLMoCR 7B 0825

OLMoCR 7B 1025

Claude 3 7 Sonnet Latest

Claude 4 Opus

Claude 4 Sonnet

Claude Haiku 4 5

Claude Opus 4 7

Claude Opus 4 8

Claude Sonnet 4 6

Cobuddy

ERNIE 4.5 21B A3B

ERNIE 4.5 21B A3B Thinking

ERNIE 4.5 300B A47B Paddle

ERNIE 4.5 VL 28B A3B

ERNIE 4.5 VL 28B A3B Thinking

ERNIE 4.5 VL 424B A47B

Seed 1.8

Seed 2.0 Code

Seed 2.0 Mini

Seed 2.0 Pro

DeepSeek V3

DeepSeek OCR

DeepSeek OCR 2

DeepSeek Prover V2 671B

DeepSeek R1

DeepSeek R1 0528

DeepSeek R1 0528 Qwen3 8B

DeepSeek R1 0528 Turbo

DeepSeek R1 Distill Llama 70B

DeepSeek R1 Distill Qwen 14B

DeepSeek R1 Distill Qwen 32B

DeepSeek R1 Turbo

DeepSeek V3

DeepSeek V3 0324

DeepSeek V3 0324 Turbo

DeepSeek V3 Turbo

DeepSeek V3.1

DeepSeek V3.1 Terminus

DeepSeek V3.2 Exp

DeepSeek V4 Flash

Codegemma 7B It

Gemini 1.5 Flash

Gemini 1.5 Flash 8B

Gemini 2.0 Flash

Gemini 2.0 Flash 001

Gemini 2.0 Flash Lite

Gemini 2.0 Flash Lite 001

Gemini 2.5 Flash Lite

Gemini 3 Flash Preview

Gemini 3 Pro Preview

Gemini 3.1 Flash Lite Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview Customtools

Gemma 1.1 7B It

Gemma 2 27B It

Gemma 2 9B It

Gemma 3 12B It

Gemma 3 27B It

Gemma 3 4B It

Gemma 4 26B A4B It

Gemma 4 31B It

Gemma 4 31B It Turbo

Gemma 4 E4b It

Ling 2.6 1T

Ling 2.6 Flash

Ring 2.6 1T

Kat Coder Pro

K EXAONE 236B A23B

Llama 2 13B Chat Hf

Llama 2 70B Chat Hf

Llama 3 70B Instruct

Llama 3 8B Instruct

Llama 3.1 8B Instruct

Llama 3.2 11B Vision Instruct

Llama 3.2 1B Instruct

Llama 3.2 3B Instruct

Llama 3.2 90B Vision Instruct

Llama 3.3 70B Instruct

Llama 3.3 70B Instruct Turbo

Llama 4 Maverick 17B 128e Instruct Turbo

Llama Guard 3 8B

Llama Guard 4 12B

Meta Llama 3 70B Instruct

Meta Llama 3 8B Instruct

Meta Llama 3.1 405B Instruct

Meta Llama 3.1 70B Instruct

Meta Llama 3.1 70B Instruct Turbo

Meta Llama 3.1 8B Instruct

Meta Llama 3.1 8B Instruct Turbo

Phi 3 Medium 4K Instruct

Phi 4

Phi 4 Multimodal Instruct

Phi 4 Reasoning Plus

Wizardlm 2 7B

Wizardlm 2 8x22b

MiniMax M1 80K

MiniMax M2

MiniMax M2.1

MiniMax M2.5

MiniMax M2.5 Highspeed

MiniMax M2.7

MiniMax M2.7 Highspeed

MiniMax M2.7 Turbo

Devstral Small 2505

Devstral Small 2507

Mistral 7B Instruct V0.1

Mistral 7B Instruct V0.2

Mistral 7B Instruct V0.3

Mistral Nemo

Mistral Nemo Instruct 2407

Mistral Small 24B Instruct 2501

Mistral Small 3.1 24B Instruct 2503

Mistral Small 3.2 24B Instruct 2506

Mixtral 8x22b Instruct V0.1

Mixtral 8x7b Instruct V0.1

Kimi K2 0905

Kimi K2 Instruct

Kimi K2 Instruct 0905

Kimi K2.5

Kimi K2.5 Turbo

Llama 3.1 Nemotron 70B Instruct

Llama 3.3 Nemotron Super 49B V1.5

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano Omni 30B A3B Reasoning

Nemotron 4 340B Instruct

Nemotron Content Safety 3.5

Nvidia Nemotron 3 Super 120B A12B

Nvidia Nemotron 3 Ultra 550B A55B Bf16

Nvidia Nemotron Nano 12B V2 VL

Nvidia Nemotron Nano 9B V2

GPT 3.5 Turbo

GPT 3.5 Turbo 16K

GPT 4

GPT 4 Turbo

GPT 4.1

GPT 4.1 Mini

GPT 4.1 Nano

GPT 4o

GPT 4o Mini

GPT 5

GPT 5 Codex

GPT 5 Pro

GPT 5.1 Codex

GPT 5.1 Codex Max

GPT 5.1 Codex Mini

GPT 5.2 Codex

GPT 5.2 Pro

GPT 5.4 Pro

GPT 5.5 Pro

GPT OSS 120B

GPT OSS 120B Turbo

GPT OSS 20B

o1

o1 Pro

o3

o3 Mini

o3 Pro

o4 Mini

QvQ 72B Preview

Qwen 2 7B Instruct

Qwen 2 VL 72B Instruct

Qwen 2.5 72B Instruct

Qwen Mt Plus

Qwen2 72B Instruct

Qwen2 7B Instruct

Qwen2.5 72B Instruct

Qwen2.5 7B Instruct

Qwen2.5 Coder 32B Instruct

Qwen2.5 Coder 7B

Qwen2.5 VL 32B Instruct

Qwen2.5 VL 72B Instruct

Qwen3 14B

Qwen3 235B A22B

Qwen3 235B A22B FP8

Qwen3 235B A22B Thinking 2507

Qwen3 30B A3B

Qwen3 30B A3B FP8

Qwen3 32B

Qwen3 32B FP8

Qwen3 4B FP8

Qwen3 8B FP8

Qwen3 Coder 30B A3B Instruct

Qwen3 Coder 480B A35B Instruct

Qwen3 Coder 480B A35B Instruct Turbo

Qwen3 Coder Next

Qwen3 Max Thinking

Qwen3 Next 80B A3B Instruct

Qwen3 Next 80B A3B Thinking

Qwen3 Omni 30B A3B Instruct

Qwen3 Omni 30B A3B Thinking

Qwen3 VL 235B A22B Thinking

Qwen3 VL 30B A3B Instruct

Qwen3 VL 30B A3B Thinking

Qwen3 VL 4B Instruct

Qwen3 VL 4B Thinking

Qwen3 VL 8B Instruct

Qwen3 VL 8B Thinking

Qwen3.5 0.8B

Qwen3.5 122B A10B

Qwen3.5 27B

Qwen3.5 2B

Qwen3.5 35B A3B

Qwen3.5 397B A17B

Qwen3.5 4B

Qwen3.5 9B

Qwen3.5 Plus

Qwen3.6 27B

Qwen3.6 35B A3B

Qwen3.6 Plus

Qwen3.7 Max

QwQ 32B

QwQ 32B Preview

Step 3.5 Flash

Step 3.7 Flash

Grok Build 0.1

MiMo V2 Flash

MiMo V2 Pro

MiMo V2.5

MiMo V2.5 Pro

Autoglm Phone 9B Multilingual

GLM 4 32B 0414

GLM 4.5

GLM 4.5 Air

GLM 4.5v

GLM 4.6

GLM 4.6v

GLM 4.7

GLM 4.7 Flash

GLM 4.7 H

GLM 5 Turbo

GLM 5.1

GLM 5v Turbo

This router fixes the purpose. To auto-assign by difficulty alone, use celon/auto instead.