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 reports Run 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
ministral-3-3b-instruct vs Z.ai: GLM 5.3 Flash	`mistralai/ministral-3-3b-instruct`	1	`z-ai/glm-5.3-flash`	48
ministral-3-8b-instruct vs MoonshotAI: Kimi K3	`mistralai/ministral-3-8b-instruct`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs nemotron-nano-12b-v2	`deepseek/deepseek-v4-flash-0731`	35	`nvidia/nemotron-nano-12b-v2`	1
DeepSeek: DeepSeek V4.1 Flash vs nemotron-nano-9b-v2	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-nano-9b-v2`	1
OpenAI: gpt-oss-120b vs palmyra-vision-7b	`openai/gpt-oss-120b`	38	`writer/palmyra-vision-7b`	1
PixVerse C1 vs Qwen: Qwen3.8 27B	`pixverse/c1`	1	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs ShengShu Vidu Q3	`moonshotai/kimi-k2.6`	27	`shengshu/vidu-q3`	1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Gemini Embedding 001	`deepseek/deepseek-v4.1-flash-1017`	24	`google/gemini-embedding-001`	2
Cohere Embed English v3.0 vs MiniMax: MiniMax M3	`cohere/embed-english-v3.0`	2	`minimax/minimax-m3`	25
Cohere Embed Multilingual v3.0 vs MoonshotAI: Kimi K2.7 Code	`cohere/embed-multilingual-v3.0`	2	`moonshotai/kimi-k2.7-code`	21
Jina AI: Jina Embedding B EN v1 vs Z.ai: GLM 5.2	`jina-ai/jina-embedding-b-en-v1`	1	`z-ai/glm-5.2`	50
abliterate-0.3-balanced vs Z.ai: GLM 5.3	`abliterate/abliterate-0.3-balanced`	1	`z-ai/glm-5.3`	50
abliterate-0.3-clever vs Z.ai: GLM 5.3 Flash	`abliterate/abliterate-0.3-clever`	1	`z-ai/glm-5.3-flash`	48
abliterate-0.3-fast vs MoonshotAI: Kimi K3	`abliterate/abliterate-0.3-fast`	1	`moonshotai/kimi-k3`	45
FLUX.2 [flex] vs DeepSeek: DeepSeek V4 Flash 0731	`black-forest-labs/flux-2-flex`	1	`deepseek/deepseek-v4-flash-0731`	35
FLUX.2 [klein] 4B vs DeepSeek: DeepSeek V4.1 Flash	`black-forest-labs/flux-2-klein-4b`	1	`deepseek/deepseek-v4.1-flash`	37
FLUX.2 [klein] 9B vs OpenAI: gpt-oss-120b	`black-forest-labs/flux-2-klein-9b`	1	`openai/gpt-oss-120b`	38
FLUX.2 [max] vs Qwen: Qwen3.8 27B	`black-forest-labs/flux-2-max`	1	`qwen/qwen3.8-27b`	33
FLUX.2 [pro] vs MoonshotAI: Kimi K2.6	`black-forest-labs/flux-2-pro`	1	`moonshotai/kimi-k2.6`	27
cohere-command-a vs DeepSeek: DeepSeek V4.1 Flash 1017	`cohere/command-a`	1	`deepseek/deepseek-v4.1-flash-1017`	24
Lucy Image 2 vs MiniMax: MiniMax M3	`decart/lucy-image-2`	1	`minimax/minimax-m3`	25
DeepSeek Fetch vs MoonshotAI: Kimi K2.7 Code	`deepseek/fetch`	1	`moonshotai/kimi-k2.7-code`	21
ElevenLabs: Eleven Flash V2.5 vs Z.ai: GLM 5.2	`elevenlabs/eleven-flash-v2.5`	1	`z-ai/glm-5.2`	50
ElevenLabs: Eleven Multilingual V2 vs Z.ai: GLM 5.3	`elevenlabs/eleven-multilingual-v2`	1	`z-ai/glm-5.3`	50
ElevenLabs: Eleven Turbo V2.5 vs Z.ai: GLM 5.3 Flash	`elevenlabs/eleven-turbo-v2.5`	1	`z-ai/glm-5.3-flash`	48
ElevenLabs: Eleven V3 vs MoonshotAI: Kimi K3	`elevenlabs/eleven-v3`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs FLUX.1 Schnell on FAL	`deepseek/deepseek-v4-flash-0731`	35	`fal/flux-1-schnell`	1
DeepSeek: DeepSeek V4.1 Flash vs nvidia/Gemma-4-31B-IT-NVFP4	`deepseek/deepseek-v4.1-flash`	37	`google/gemma-4-31b-it-nvfp4`	1
Krea 2 Medium vs OpenAI: gpt-oss-120b	`krea/krea-2-medium`	1	`openai/gpt-oss-120b`	38
meta/llama-3.2-90b-vision-instruct vs Qwen: Qwen3.8 27B	`meta-llama/llama-3.2-90b-vision-instruct`	1	`qwen/qwen3.8-27b`	33
Microsoft: MAI-Voice-2.1 vs MoonshotAI: Kimi K2.6	`microsoft/mai-voice-2.1`	1	`moonshotai/kimi-k2.6`	27
DeepSeek: DeepSeek V4.1 Flash 1017 vs Microsoft: MAI-Voice-2.1-Flash	`deepseek/deepseek-v4.1-flash-1017`	24	`microsoft/mai-voice-2.1-flash`	1
MiniMax: MiniMax M3 vs mistralai/mistral-large-4-1t-a52b	`minimax/minimax-m3`	25	`mistralai/mistral-large-4-1t-a52b`	1
mistral-medium-3.5-128b vs MoonshotAI: Kimi K2.7 Code	`mistralai/mistral-medium-3.5-128b`	1	`moonshotai/kimi-k2.7-code`	21
Mistral: Voxtral 4B TTS vs Z.ai: GLM 5.2	`mistralai/voxtral-4b-tts-2603`	1	`z-ai/glm-5.2`	50
Voxtral Mini Transcribe 2 vs Z.ai: GLM 5.3	`mistralai/voxtral-mini-2602`	1	`z-ai/glm-5.3`	50
Voxtral Mini 3B vs Z.ai: GLM 5.3 Flash	`mistralai/voxtral-mini-3b-2507`	1	`z-ai/glm-5.3-flash`	48
Mistral: Voxtral Mini TTS vs MoonshotAI: Kimi K3	`mistralai/voxtral-mini-tts-2603`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	`deepseek/deepseek-v4-flash-0731`	35	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	1
DeepSeek: DeepSeek V4.1 Flash vs nvidia/nemotron-3.5-bolt-e4b	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3.5-bolt-e4b`	1
chat-latest vs OpenAI: gpt-oss-120b	`openai/chat-latest`	2	`openai/gpt-oss-120b`	38
GPT Image 2.5 Flare vs Qwen: Qwen3.8 27B	`openai/gpt-image-2.5-flare`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs GPT Image 2.5 Sunburst	`moonshotai/kimi-k2.6`	27	`openai/gpt-image-2.5-sunburst`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI Whisper	`deepseek/deepseek-v4.1-flash-1017`	24	`openai/whisper-1`	1
MiniMax: MiniMax M3 vs Whisper Large V3	`minimax/minimax-m3`	25	`openai/whisper-large-v3`	1
MoonshotAI: Kimi K2.7 Code vs Whisper Large V3 Turbo	`moonshotai/kimi-k2.7-code`	21	`openai/whisper-large-v3-turbo`	1
poolside/laguna-xs-2.1 vs Z.ai: GLM 5.2	`poolside/laguna-xs-2.1`	1	`z-ai/glm-5.2`	50
Qwen Plus Character vs Z.ai: GLM 5.3	`qwen/qwen-plus-character`	1	`z-ai/glm-5.3`	50
Qwen: Qwen3 TTS vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-tts`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Recraft V2	`moonshotai/kimi-k3`	45	`recraft/recraftv2`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Recraft V3	`deepseek/deepseek-v4-flash-0731`	35	`recraft/recraftv3`	1
DeepSeek: DeepSeek V4.1 Flash vs Recraft V4	`deepseek/deepseek-v4.1-flash`	37	`recraft/recraftv4`	1
OpenAI: gpt-oss-120b vs Recraft V4.1	`openai/gpt-oss-120b`	38	`recraft/recraftv4_1`	1
Qwen: Qwen3.8 27B vs Recraft V4.1 Pro	`qwen/qwen3.8-27b`	33	`recraft/recraftv4_1_pro`	1
MoonshotAI: Kimi K2.6 vs Recraft V4.1 Utility	`moonshotai/kimi-k2.6`	27	`recraft/recraftv4_1_utility`	1
DeepSeek: DeepSeek V4.1 Flash 1017 vs Recraft V4.1 Utility Pro	`deepseek/deepseek-v4.1-flash-1017`	24	`recraft/recraftv4_1_utility_pro`	1
MiniMax: MiniMax M3 vs Recraft V4 Pro	`minimax/minimax-m3`	25	`recraft/recraftv4_pro`	1
MoonshotAI: Kimi K2.7 Code vs ReMM-SLerp	`moonshotai/kimi-k2.7-code`	21	`undi95/remm-slerp-l2-13b`	1
solar-pro4 vs Z.ai: GLM 5.2	`upstage/solar-pro4`	1	`z-ai/glm-5.2`	50
grok-4-1-fast-non-reasoning vs Z.ai: GLM 5.3	`x-ai/grok-4.1-fast-non-reasoning`	1	`z-ai/glm-5.3`	50
grok-4-1-fast-reasoning vs Z.ai: GLM 5.3 Flash	`x-ai/grok-4.1-fast-reasoning`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs grok-4-20-non-reasoning	`moonshotai/kimi-k3`	45	`x-ai/grok-4.20-non-reasoning`	1
DeepSeek: DeepSeek V4 Flash 0731 vs xAI: Grok Voice TTS 1.0	`deepseek/deepseek-v4-flash-0731`	35	`x-ai/grok-voice-tts-1.0`	1
DeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok 4.20 Multi-Agent	`deepseek/deepseek-v4.1-flash`	37	`x-ai/grok-4.20-multi-agent`	0
OpenAI: gpt-oss-120b vs Grok 4.6	`openai/gpt-oss-120b`	38	`x-ai/grok4.6`	1
OpenAI: GPT-5.4 vs Qwen: Qwen3.8 27B	`openai/gpt-5.4`	2	`qwen/qwen3.8-27b`	33
MoonshotAI: Kimi K2.6 vs OpenAI: GPT-5.4 Pro	`moonshotai/kimi-k2.6`	27	`openai/gpt-5.4-pro`	2
DeepSeek: DeepSeek V4.1 Flash 1017 vs Google: Gemini 3.1 Flash Lite Preview	`deepseek/deepseek-v4.1-flash-1017`	24	`google/gemini-3.1-flash-lite-preview`	1
MiniMax: MiniMax M3 vs TrustedRouter Dev 1.0	`minimax/minimax-m3`	25	`trustedrouter/dev-1.0`	0
MoonshotAI: Kimi K2.7 Code vs TrustedRouter Gev 1.0	`moonshotai/kimi-k2.7-code`	21	`trustedrouter/gev-1.0`	0
TrustedRouter Zev 1.0 vs Z.ai: GLM 5.2	`trustedrouter/zev-1.0`	0	`z-ai/glm-5.2`	50
anthropic/claude-opus-4-7 vs Z.ai: GLM 5.3	`anthropic/claude-opus-4-7`	1	`z-ai/glm-5.3`	50
anthropic/claude-opus-4-8 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-opus-4-8`	1	`z-ai/glm-5.3-flash`	48
Claude Opus 4.6 AWS vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4.6-aws`	0	`moonshotai/kimi-k3`	45
Claude Opus 4.6 Coding vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-opus-4.6-coding`	0	`deepseek/deepseek-v4-flash-0731`	35
Claude Opus 4.7 AWS vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-opus-4.7-aws`	0	`deepseek/deepseek-v4.1-flash`	37
Claude Opus 4.7 Coding vs OpenAI: gpt-oss-120b	`anthropic/claude-opus-4.7-coding`	0	`openai/gpt-oss-120b`	38
Claude Opus 4.8 AWS vs Qwen: Qwen3.8 27B	`anthropic/claude-opus-4.8-aws`	0	`qwen/qwen3.8-27b`	33
Claude Opus 4.8 Coding vs MoonshotAI: Kimi K2.6	`anthropic/claude-opus-4.8-coding`	0	`moonshotai/kimi-k2.6`	27
anthropic/claude-opus-5-5 vs DeepSeek: DeepSeek V4.1 Flash 1017	`anthropic/claude-opus-5-5`	1	`deepseek/deepseek-v4.1-flash-1017`	24
Claude Opus 5 AWS vs MiniMax: MiniMax M3	`anthropic/claude-opus-5-aws`	0	`minimax/minimax-m3`	25
anthropic/claude-sonnet-4-6 vs MoonshotAI: Kimi K2.7 Code	`anthropic/claude-sonnet-4-6`	1	`moonshotai/kimi-k2.7-code`	21
anthropic/claude-sonnet-5-5 vs Z.ai: GLM 5.2	`anthropic/claude-sonnet-5-5`	1	`z-ai/glm-5.2`	50
Claude Sonnet 5 AWS vs Z.ai: GLM 5.3	`anthropic/claude-sonnet-5-aws`	0	`z-ai/glm-5.3`	50
TrustedRouter Mev 1.0 vs Z.ai: GLM 5.3 Flash	`trustedrouter/mev-1.0`	0	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-5.4 Nano	`moonshotai/kimi-k3`	45	`openai/gpt-5.4-nano`	2
DeepSeek: DeepSeek V4 Flash 0731 vs InclusionAI: Ling-3.0-flash-fin	`deepseek/deepseek-v4-flash-0731`	35	`inclusionai/ling-3.0-flash-fin`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen/Qwen3-235B-A22B-Instruct-2507-FP8	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3-235b-a22b-instruct-2507-fp8`	1
OpenAI: gpt-oss-120b vs Qwen3 Next 80B A3B Thinking	`openai/gpt-oss-120b`	38	`qwen/qwen3-next-80b-a3b-thinking`	1
Qwen: Qwen3.8 27B vs Qwen3.8 Max 0902	`qwen/qwen3.8-27b`	33	`qwen/qwen3.8-max-0902`	1
MoonshotAI: Kimi K2.6 vs Tencent: Hy3 preview	`moonshotai/kimi-k2.6`	27	`tencent/hy3-preview`	1
DeepSeek: DeepSeek V4.1 Flash 1017 vs TrustedRouter Gemmev 1.0	`deepseek/deepseek-v4.1-flash-1017`	24	`trustedrouter/gemmev-1.0`	0
MiniMax: MiniMax M3 vs Qwen/Qwen3-235B-A22B-Thinking-2507-FP8	`minimax/minimax-m3`	25	`qwen/qwen3-235b-a22b-thinking-2507-fp8`	1
MoonshotAI: Kimi K2.7 Code vs Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8	`moonshotai/kimi-k2.7-code`	21	`qwen/qwen3-coder-480b-a35b-instruct-fp8`	1
Proxy: zai-org/GLM-4.7 vs Z.ai: GLM 5.2	`z-ai/glm-4.7-fp8`	1	`z-ai/glm-5.2`	50
anthropic/claude-haiku-4-5 vs Z.ai: GLM 5.3	`anthropic/claude-haiku-4-5`	1	`z-ai/glm-5.3`	50
Claude Haiku 4.5 20251001 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-haiku-4.5-20251001`	0	`z-ai/glm-5.3-flash`	48
Claude Haiku 4.5 20251001 AWS vs MoonshotAI: Kimi K3	`anthropic/claude-haiku-4.5-20251001-aws`	0	`moonshotai/kimi-k3`	45
Claude Haiku 4.5 20251001 Coding vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-haiku-4.5-20251001-coding`	0	`deepseek/deepseek-v4-flash-0731`	35
Claude Opus 4 20250514 vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-opus-4-20250514`	0	`deepseek/deepseek-v4.1-flash`	37