Find a model

Browse the full catalog →
OpenAI compatible API · Attested · Public status

Compare AI models

Compare context, provider routes, pricing, privacy posture, and measured performance across the TrustedRouter model catalog.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Measured speed

Find the fastest routes.

Compare provider TTFT, throughput, and uptime from routed probes.

Open leaderboard → Open weights

Compare open models.

Browse DeepSeek, GLM, Gemma, Kimi, MiniMax, Qwen, and other open routes.

Browse models → Privacy

Require ZDR or confidential routes.

Separate gateway attestation from each downstream provider's privacy posture.

Review privacy →

Current comparison, preserved evidence.

Comparison pages use the current catalog and live route measurements. Monthly reports preserve the historical evidence after prices and provider performance change.

Monthly reportsRun your own eval
Model comparisons

Pick two models. Compare the routes that actually serve them.

Every comparison uses the current TrustedRouter catalog, prices, provider posture, and measured route data.

Comparison First model Routes Second model Routes
MiniMax: MiniMax M3 vs OpenAI: GPT-4o minimax/minimax-m3 25 openai/gpt-4o 2
MoonshotAI: Kimi K2.7 Code vs OpenAI: GPT-4o-mini moonshotai/kimi-k2.7-code 21 openai/gpt-4o-mini 2
gpt-oss-safeguard-20b vs Z.ai: GLM 5.2 openai/gpt-oss-safeguard-20b 1 z-ai/glm-5.2 50
Qwen: Qwen2.5 VL 72B Instruct vs Z.ai: GLM 5.3 qwen/qwen2.5-vl-72b-instruct 2 z-ai/glm-5.3 50
Qwen: Qwen3 235B A22B Thinking 2507 vs Z.ai: GLM 5.3 Flash qwen/qwen3-235b-a22b-thinking-2507 2 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs Qwen3 VL 235B moonshotai/kimi-k3 45 qwen/qwen3-vl-235b-a22b 2
DeepSeek: DeepSeek V4 Flash 0731 vs Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR deepseek/deepseek-v4-flash-0731 35 intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar 1
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b vs DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-r1-distill-qwen-32b 1 deepseek/deepseek-v4.1-flash 37
Meta: Llama 3.2 3B Instruct vs OpenAI: gpt-oss-120b meta-llama/llama-3.2-3b-instruct 1 openai/gpt-oss-120b 38
alia-salamandra:40b vs Qwen: Qwen3.8 27B bsc-lt/alia-40b-instruct-2601 1 qwen/qwen3.8-27b 33
Cloudflare Clairic vs MoonshotAI: Kimi K2.6 cloudflare/clairic 1 moonshotai/kimi-k2.6 27
Cloudflare Clef-Flash vs DeepSeek: DeepSeek V4.1 Flash 1017 cloudflare/clef-flash 2 deepseek/deepseek-v4.1-flash-1017 24
Nano Banana 2 vs MiniMax: MiniMax M3 google/gemini-3.1-flash-image 2 minimax/minimax-m3 25
Nano Banana 2 vs MoonshotAI: Kimi K2.7 Code google/gemini-3.1-flash-image-preview 2 moonshotai/kimi-k2.7-code 21
Nemotron Nano 3 Omni vs Z.ai: GLM 5.2 nvidia/nemotron-3-nano-omni 2 z-ai/glm-5.2 50
Qwen3 Omni 30B A3B Thinking vs Z.ai: GLM 5.3 qwen/qwen3-omni-30b-a3b-thinking 2 z-ai/glm-5.3 50
Z.ai: GLM 5.3 Flash vs AutoGLM Phone 9B Multilingual z-ai/glm-5.3-flash 48 zai-org/autoglm-phone-9b-multilingual 2
MoonshotAI: Kimi K3 vs GLM 4.5V moonshotai/kimi-k3 45 zai-org/glm-4.5v 2
DeepSeek: DeepSeek V4 Flash 0731 vs WizardLM 2 8x22B deepseek/deepseek-v4-flash-0731 35 microsoft/wizardlm-2-8x22b 2
DeepSeek R1 Turbo vs DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-r1-turbo 2 deepseek/deepseek-v4.1-flash 37
@cf/meta/llama-3.2-1b-instruct vs OpenAI: gpt-oss-120b meta-llama/llama-3.2-1b-instruct 1 openai/gpt-oss-120b 38
Conversation Summary vs Qwen: Qwen3.8 27B neurometric/conversation-summary 1 qwen/qwen3.8-27b 33
MoonshotAI: Kimi K2.6 vs Document Structured Extraction moonshotai/kimi-k2.6 27 neurometric/document-structured-extraction 1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Grounded Document QA deepseek/deepseek-v4.1-flash-1017 24 neurometric/grounded-document-qa 1
MiniMax: MiniMax M3 vs Qwen: Qwen3 8B minimax/minimax-m3 25 qwen/qwen3-8b 1
AionLabs: Aion-RP 1.0 (8B) vs MoonshotAI: Kimi K2.7 Code aion-labs/aion-rp-llama-3.1-8b 1 moonshotai/kimi-k2.7-code 21
granite-4.1-8b vs Z.ai: GLM 5.2 ibm-granite/granite-4.1-8b 1 z-ai/glm-5.2 50
Jina AI: Jina Code Embeddings 0.5b vs Z.ai: GLM 5.3 jina-ai/jina-code-embeddings-0.5b 1 z-ai/glm-5.3 50
Jina AI: Jina Code Embeddings 1.5b vs Z.ai: GLM 5.3 Flash jina-ai/jina-code-embeddings-1.5b 1 z-ai/glm-5.3-flash 48
Jina AI: Jina Embeddings v4 vs MoonshotAI: Kimi K3 jina-ai/jina-embeddings-v4 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4 Flash 0731 vs Jina AI: Jina Embeddings v5 Omni Small deepseek/deepseek-v4-flash-0731 35 jina-ai/jina-embeddings-v5-omni-small 1
DeepSeek: DeepSeek V4.1 Flash vs Jina AI: Jina Embeddings v5 Text Small deepseek/deepseek-v4.1-flash 37 jina-ai/jina-embeddings-v5-text-small 1
Microsoft Decision-1 vs OpenAI: gpt-oss-120b microsoft/microsoft-decision-1 1 openai/gpt-oss-120b 38
Mistral: Mistral Small 3 vs Qwen: Qwen3.8 27B mistralai/mistral-small-24b-instruct-2501 2 qwen/qwen3.8-27b 33
Voxtral Small 24B vs MoonshotAI: Kimi K2.6 mistralai/voxtral-small-24b 1 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Classification Router deepseek/deepseek-v4.1-flash-1017 24 neurometric/classification-router 1
MiniMax: MiniMax M3 vs tool-choice minimax/minimax-m3 25 neurometric/tool-choice 1
MoonshotAI: Kimi K2.7 Code vs Qwen/Qwen-AgentWorld-35B-A3B moonshotai/kimi-k2.7-code 21 qwen/qwen-agentworld-35b-a3b 1
Qwen/Qwen2.5-72B-Instruct vs Z.ai: GLM 5.2 qwen/qwen2.5-72b-instruct 2 z-ai/glm-5.2 50
@cf/qwen/qwen2.5-coder-32b-instruct vs Z.ai: GLM 5.3 qwen/qwen2.5-coder-32b-instruct 1 z-ai/glm-5.3 50
@cf/qwen/qwen3-30b-a3b-fp8 vs Z.ai: GLM 5.3 Flash qwen/qwen3-30b-a3b-fp8 1 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs Qwen3-Embedding 4B moonshotai/kimi-k3 45 qwen/qwen3-embedding-4b 1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen/Qwen3.5-2B deepseek/deepseek-v4-flash-0731 35 qwen/qwen3.5-2b 1
DeepSeek: DeepSeek V4.1 Flash vs Qwen/Qwen3.5-4B deepseek/deepseek-v4.1-flash 37 qwen/qwen3.5-4b 1
OpenAI: gpt-oss-120b vs Qwen/WebWorld-8B openai/gpt-oss-120b 38 qwen/webworld-8b 1
Qwen: Qwen3.8 27B vs TheDrummer: Skyfall 36B V2 qwen/qwen3.8-27b 33 thedrummer/skyfall-36b-v2 2
MoonshotAI: Kimi K2.6 vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B moonshotai/kimi-k2.6 27 xiaomi/mimo-v2.6-distill-qwen-9b 1
DeepSeek: DeepSeek V4.1 Flash 1017 vs 0GM-1.0-35B-A3B-SIA deepseek/deepseek-v4.1-flash-1017 24 zero-g/0gm-1.0-35b-a3b-sia 1
@cf/meta/llama-3.1-8b-instruct-fp8 vs MiniMax: MiniMax M3 meta-llama/llama-3.1-8b-instruct-fp8 1 minimax/minimax-m3 25
MoonshotAI: Kimi K2.7 Code vs TypeSafe AI Jev moonshotai/kimi-k2.7-code 21 typesafe-ai/jev 1
Voyage 3 Large vs Z.ai: GLM 5.2 voyage/voyage-3-large 2 z-ai/glm-5.2 50
apertus-70b vs Z.ai: GLM 5.3 swiss-ai/apertus-70b-instruct 2 z-ai/glm-5.3 50
@cf/meta/llama-3.3-70b-instruct-fp8-fast vs Z.ai: GLM 5.3 Flash meta-llama/llama-3.3-70b-instruct-fp8-fast 1 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs @cf/qwen/qwq-32b moonshotai/kimi-k3 45 qwen/qwq-32b 1
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-3.5 Turbo deepseek/deepseek-v4-flash-0731 35 openai/gpt-3.5-turbo 2
elephant-1 vs DeepSeek: DeepSeek V4.1 Flash decision-models/baseten-elephant-9b-latest 2 deepseek/deepseek-v4.1-flash 37
joey-1 vs OpenAI: gpt-oss-120b decision-models/baseten-joey-2b-latest 2 openai/gpt-oss-120b 38
mammoth-1 vs Qwen: Qwen3.8 27B decision-models/baseten-mammoth-27b-latest 2 qwen/qwen3.8-27b 33
Microsoft: Phi 4 vs MoonshotAI: Kimi K2.6 microsoft/phi-4 2 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Reka Edge 2603 deepseek/deepseek-v4.1-flash-1017 24 reka/reka-edge-2603 1
Decart Lucy 2.5 vs MiniMax: MiniMax M3 decart/lucy-2.5 1 minimax/minimax-m3 25
Decart Lucy Restyle 2 vs MoonshotAI: Kimi K2.7 Code decart/lucy-restyle-2 1 moonshotai/kimi-k2.7-code 21
Decart Lucy VTON 3.5 vs Z.ai: GLM 5.2 decart/lucy-vton-3.5 1 z-ai/glm-5.2 50
MiniMax H3 Max vs Z.ai: GLM 5.3 minimax/h3-max 1 z-ai/glm-5.3 50
xAI Grok Imagine Video vs Z.ai: GLM 5.3 Flash x-ai/grok-imagine-video 1 z-ai/glm-5.3-flash 48
Decision Models s1-pro (EU) vs MoonshotAI: Kimi K3 decisionmodelsio-eu/s1-pro 1 moonshotai/kimi-k3 45
Decision Models s1-pro-2 (EU) vs DeepSeek: DeepSeek V4 Flash 0731 decisionmodelsio-eu/s1-pro-2 1 deepseek/deepseek-v4-flash-0731 35
Decision Models s1-pro-3 (EU) vs DeepSeek: DeepSeek V4.1 Flash decisionmodelsio-eu/s1-pro-3 1 deepseek/deepseek-v4.1-flash 37
Decision Models s1-pro (GLOBAL) vs OpenAI: gpt-oss-120b decisionmodelsio/s1-pro 1 openai/gpt-oss-120b 38
Decision Models s1-pro-2 (GLOBAL) vs Qwen: Qwen3.8 27B decisionmodelsio/s1-pro-2 1 qwen/qwen3.8-27b 33
Decision Models s1-pro-3 (GLOBAL) vs MoonshotAI: Kimi K2.6 decisionmodelsio/s1-pro-3 1 moonshotai/kimi-k2.6 27
DeepSeek OCR vs DeepSeek: DeepSeek V4.1 Flash 1017 deepseek/deepseek-ocr 1 deepseek/deepseek-v4.1-flash-1017 24
Google: Gemini 3.8 Flash Lite TTS vs MiniMax: MiniMax M3 google/gemini-3.8-flash-lite-tts 1 minimax/minimax-m3 25
Google: Gemini 3.8 Flash TTS vs MoonshotAI: Kimi K2.7 Code google/gemini-3.8-flash-tts 1 moonshotai/kimi-k2.7-code 21
MythoMax 13B vs Z.ai: GLM 5.2 gryphe/mythomax-l2-13b 2 z-ai/glm-5.2 50
Jina AI: Jina Clip v1 vs Z.ai: GLM 5.3 jina-ai/jina-clip-v1 1 z-ai/glm-5.3 50
Jina AI: Jina Clip v2 vs Z.ai: GLM 5.3 Flash jina-ai/jina-clip-v2 1 z-ai/glm-5.3-flash 48
Jina AI: Jina Colbert v2 vs MoonshotAI: Kimi K3 jina-ai/jina-colbert-v2 1 moonshotai/kimi-k3 45
DeepSeek: DeepSeek V4 Flash 0731 vs Jina AI: Jina Embeddings v2 Base Code deepseek/deepseek-v4-flash-0731 35 jina-ai/jina-embeddings-v2-base-code 1
DeepSeek: DeepSeek V4.1 Flash vs Jina AI: Jina Embeddings v2 Base DE deepseek/deepseek-v4.1-flash 37 jina-ai/jina-embeddings-v2-base-de 1
Jina AI: Jina Embeddings v2 Base EN vs OpenAI: gpt-oss-120b jina-ai/jina-embeddings-v2-base-en 1 openai/gpt-oss-120b 38
Jina AI: Jina Embeddings v2 Base ES vs Qwen: Qwen3.8 27B jina-ai/jina-embeddings-v2-base-es 1 qwen/qwen3.8-27b 33
Jina AI: Jina Embeddings v2 Base ZH vs MoonshotAI: Kimi K2.6 jina-ai/jina-embeddings-v2-base-zh 1 moonshotai/kimi-k2.6 27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Jina AI: Jina Embeddings v3 deepseek/deepseek-v4.1-flash-1017 24 jina-ai/jina-embeddings-v3 1
Jina AI: Jina Embeddings v5 Omni Nano vs MiniMax: MiniMax M3 jina-ai/jina-embeddings-v5-omni-nano 1 minimax/minimax-m3 25
Jina AI: Jina Embeddings v5 Text Nano vs MoonshotAI: Kimi K2.7 Code jina-ai/jina-embeddings-v5-text-nano 1 moonshotai/kimi-k2.7-code 21
Nomic Embed Text vs Z.ai: GLM 5.2 nomic-ai/nomic-embed-text 2 z-ai/glm-5.2 50
Sao10K/L3-8B-Lunaris-v1-Turbo vs Z.ai: GLM 5.3 sao10k/l3-8b-lunaris-v1-turbo 2 z-ai/glm-5.3 50
Llama 3 8B Stheno V3.2 vs Z.ai: GLM 5.3 Flash Sao10K/L3-8B-Stheno-v3.2 2 z-ai/glm-5.3-flash 48
MoonshotAI: Kimi K3 vs OpenAI Text Embedding 3 Large moonshotai/kimi-k3 45 openai/text-embedding-3-large 2
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI Text Embedding 3 Small deepseek/deepseek-v4-flash-0731 35 openai/text-embedding-3-small 2
DeepSeek: DeepSeek V4.1 Flash vs OpenAI Text Embedding Ada 002 deepseek/deepseek-v4.1-flash 37 openai/text-embedding-ada-002 2
Decision Models s1-fast (EU) vs OpenAI: gpt-oss-120b decisionmodelsio-eu/s1-fast 1 openai/gpt-oss-120b 38
Decision Models s1-fast-2 (EU) vs Qwen: Qwen3.8 27B decisionmodelsio-eu/s1-fast-2 1 qwen/qwen3.8-27b 33
Decision Models s1-fast (GLOBAL) vs MoonshotAI: Kimi K2.6 decisionmodelsio/s1-fast 1 moonshotai/kimi-k2.6 27
Decision Models s1-fast-2 (GLOBAL) vs DeepSeek: DeepSeek V4.1 Flash 1017 decisionmodelsio/s1-fast-2 1 deepseek/deepseek-v4.1-flash-1017 24
MiniMax: MiniMax M3 vs Nemotron-3.5-Lightning minimax/minimax-m3 25 nvidia/nemotron-3_5-lightning 2
MoonshotAI: Kimi K2.7 Code vs openbmb/MiniCPM-V-4_5 moonshotai/kimi-k2.7-code 21 openbmb/MiniCPM-V-4_5 2
devstral-2-123b vs Z.ai: GLM 5.2 mistralai/devstral-2-123b 1 z-ai/glm-5.2 50
magistral-small-2509 vs Z.ai: GLM 5.3 mistralai/magistral-small-2509 1 z-ai/glm-5.3 50
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

By continuing you agree to the terms of service and privacy policy.