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
Cohere Embed Multilingual v3.0 vs DeepSeek: DeepSeek V4.1 Flash	`cohere/embed-multilingual-v3.0`	2	`deepseek/deepseek-v4.1-flash`	37
Jina AI: Jina Embedding B EN v1 vs OpenAI: gpt-oss-120b	`jina-ai/jina-embedding-b-en-v1`	1	`openai/gpt-oss-120b`	37
abliterate-0.3-balanced vs Qwen: Qwen3.8 27B	`abliterate/abliterate-0.3-balanced`	1	`qwen/qwen3.8-27b`	30
abliterate-0.3-clever vs MoonshotAI: Kimi K2.6	`abliterate/abliterate-0.3-clever`	1	`moonshotai/kimi-k2.6`	27
abliterate-0.3-fast vs Google: Gemma 4 31B	`abliterate/abliterate-0.3-fast`	1	`google/gemma-4-31b-it`	26
FLUX.2 [flex] vs DeepSeek: DeepSeek V4 Pro 0423	`black-forest-labs/flux-2-flex`	1	`deepseek/deepseek-v4-pro`	26
FLUX.2 [klein] 4B vs MiniMax: MiniMax M3	`black-forest-labs/flux-2-klein-4b`	1	`minimax/minimax-m3`	25
FLUX.2 [klein] 9B vs Z.ai: GLM 5.3	`black-forest-labs/flux-2-klein-9b`	1	`z-ai/glm-5.3`	50
FLUX.2 [max] vs Z.ai: GLM 5.2	`black-forest-labs/flux-2-max`	1	`z-ai/glm-5.2`	48
FLUX.2 [pro] vs Z.ai: GLM 5.3 Flash	`black-forest-labs/flux-2-pro`	1	`z-ai/glm-5.3-flash`	48
FLUX.1 Schnell vs MoonshotAI: Kimi K3	`black-forest-labs/flux.1-schnell`	1	`moonshotai/kimi-k3`	45
cohere-command-a vs DeepSeek: DeepSeek V4 Flash 0731	`cohere/command-a`	1	`deepseek/deepseek-v4-flash-0731`	35
Lucy Image 2 vs DeepSeek: DeepSeek V4.1 Flash	`decart/lucy-image-2`	1	`deepseek/deepseek-v4.1-flash`	37
DeepSeek Fetch vs OpenAI: gpt-oss-120b	`deepseek/fetch`	1	`openai/gpt-oss-120b`	37
ElevenLabs: Eleven Flash V2.5 vs Qwen: Qwen3.8 27B	`elevenlabs/eleven-flash-v2.5`	1	`qwen/qwen3.8-27b`	30
ElevenLabs: Eleven Multilingual V2 vs MoonshotAI: Kimi K2.6	`elevenlabs/eleven-multilingual-v2`	1	`moonshotai/kimi-k2.6`	27
ElevenLabs: Eleven Turbo V2.5 vs Google: Gemma 4 31B	`elevenlabs/eleven-turbo-v2.5`	1	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs ElevenLabs: Eleven V3	`deepseek/deepseek-v4-pro`	26	`elevenlabs/eleven-v3`	1
FLUX.1 Schnell on FAL vs MiniMax: MiniMax M3	`fal/flux-1-schnell`	1	`minimax/minimax-m3`	25
nvidia/Gemma-4-31B-IT-NVFP4 vs Z.ai: GLM 5.3	`google/gemma-4-31b-it-nvfp4`	1	`z-ai/glm-5.3`	50
Krea 2 Medium vs Z.ai: GLM 5.2	`krea/krea-2-medium`	1	`z-ai/glm-5.2`	48
meta/llama-3.2-90b-vision-instruct vs Z.ai: GLM 5.3 Flash	`meta-llama/llama-3.2-90b-vision-instruct`	1	`z-ai/glm-5.3-flash`	48
Microsoft: MAI-Voice-2.1 vs MoonshotAI: Kimi K3	`microsoft/mai-voice-2.1`	1	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs Microsoft: MAI-Voice-2.1-Flash	`deepseek/deepseek-v4-flash-0731`	35	`microsoft/mai-voice-2.1-flash`	1
DeepSeek: DeepSeek V4.1 Flash vs mistral-medium-3.5-128b	`deepseek/deepseek-v4.1-flash`	37	`mistralai/mistral-medium-3.5-128b`	1
Mistral: Voxtral 4B TTS vs OpenAI: gpt-oss-120b	`mistralai/voxtral-4b-tts-2603`	1	`openai/gpt-oss-120b`	37
Voxtral Mini Transcribe 2 vs Qwen: Qwen3.8 27B	`mistralai/voxtral-mini-2602`	1	`qwen/qwen3.8-27b`	30
Mistral: Voxtral Mini TTS vs MoonshotAI: Kimi K2.6	`mistralai/voxtral-mini-tts-2603`	1	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	`google/gemma-4-31b-it`	26	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	1
DeepSeek: DeepSeek V4 Pro 0423 vs chat-latest	`deepseek/deepseek-v4-pro`	26	`openai/chat-latest`	2
MiniMax: MiniMax M3 vs gpt-3.5-turbo-0125	`minimax/minimax-m3`	25	`openai/gpt-3.5-turbo-0125`	2
gpt-4-0613 vs Z.ai: GLM 5.3	`openai/gpt-4-0613`	2	`z-ai/glm-5.3`	50
GPT Image 2.5 Flare vs Z.ai: GLM 5.2	`openai/gpt-image-2.5-flare`	2	`z-ai/glm-5.2`	48
GPT Image 2.5 Sunburst vs Z.ai: GLM 5.3 Flash	`openai/gpt-image-2.5-sunburst`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI Whisper	`moonshotai/kimi-k3`	45	`openai/whisper-1`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Whisper Large V3 Turbo	`deepseek/deepseek-v4-flash-0731`	35	`openai/whisper-large-v3-turbo`	1
DeepSeek: DeepSeek V4.1 Flash vs poolside/laguna-xs-2.1	`deepseek/deepseek-v4.1-flash`	37	`poolside/laguna-xs-2.1`	1
OpenAI: gpt-oss-120b vs Qwen Plus Character	`openai/gpt-oss-120b`	37	`qwen/qwen-plus-character`	1
Qwen: Qwen3 TTS vs Qwen: Qwen3.8 27B	`qwen/qwen3-tts`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Recraft V2	`moonshotai/kimi-k2.6`	27	`recraft/recraftv2`	1
Google: Gemma 4 31B vs Recraft V3	`google/gemma-4-31b-it`	26	`recraft/recraftv3`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Recraft V4	`deepseek/deepseek-v4-pro`	26	`recraft/recraftv4`	1
MiniMax: MiniMax M3 vs Recraft V4.1	`minimax/minimax-m3`	25	`recraft/recraftv4_1`	1
Recraft V4.1 Pro vs Z.ai: GLM 5.3	`recraft/recraftv4_1_pro`	1	`z-ai/glm-5.3`	50
Recraft V4.1 Utility vs Z.ai: GLM 5.2	`recraft/recraftv4_1_utility`	1	`z-ai/glm-5.2`	48
Recraft V4.1 Utility Pro vs Z.ai: GLM 5.3 Flash	`recraft/recraftv4_1_utility_pro`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Recraft V4 Pro	`moonshotai/kimi-k3`	45	`recraft/recraftv4_pro`	1
DeepSeek: DeepSeek V4 Flash 0731 vs solar-pro2	`deepseek/deepseek-v4-flash-0731`	35	`upstage/solar-pro2`	1
DeepSeek: DeepSeek V4.1 Flash vs solar-pro3	`deepseek/deepseek-v4.1-flash`	37	`upstage/solar-pro3`	1
OpenAI: gpt-oss-120b vs solar-pro4	`openai/gpt-oss-120b`	37	`upstage/solar-pro4`	1
Qwen: Qwen3.8 27B vs grok-4-1-fast-non-reasoning	`qwen/qwen3.8-27b`	30	`x-ai/grok-4.1-fast-non-reasoning`	1
MoonshotAI: Kimi K2.6 vs grok-4-1-fast-reasoning	`moonshotai/kimi-k2.6`	27	`x-ai/grok-4.1-fast-reasoning`	1
Google: Gemma 4 31B vs grok-4-20-non-reasoning	`google/gemma-4-31b-it`	26	`x-ai/grok-4.20-non-reasoning`	1
DeepSeek: DeepSeek V4 Pro 0423 vs xAI: Grok Voice TTS 1.0	`deepseek/deepseek-v4-pro`	26	`x-ai/grok-voice-tts-1.0`	1
MiniMax: MiniMax M3 vs SpaceXAI: Grok 4.20 Multi-Agent	`minimax/minimax-m3`	25	`x-ai/grok-4.20-multi-agent`	0
Grok 4.6 vs Z.ai: GLM 5.3	`x-ai/grok4.6`	1	`z-ai/glm-5.3`	50
OpenAI: GPT-5.4 vs Z.ai: GLM 5.2	`openai/gpt-5.4`	2	`z-ai/glm-5.2`	48
OpenAI: GPT-5.4 Pro vs Z.ai: GLM 5.3 Flash	`openai/gpt-5.4-pro`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-5.5 Pro	`moonshotai/kimi-k3`	45	`openai/gpt-5.5-pro`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemini 3.1 Flash Lite Preview	`deepseek/deepseek-v4-flash-0731`	35	`google/gemini-3.1-flash-lite-preview`	1
DeepSeek: DeepSeek V4.1 Flash vs TrustedRouter Dev 1.0	`deepseek/deepseek-v4.1-flash`	37	`trustedrouter/dev-1.0`	0
OpenAI: gpt-oss-120b vs TrustedRouter Gev 1.0	`openai/gpt-oss-120b`	37	`trustedrouter/gev-1.0`	0
Qwen: Qwen3.8 27B vs TrustedRouter Zev 1.0	`qwen/qwen3.8-27b`	30	`trustedrouter/zev-1.0`	0
anthropic/claude-opus-4-7 vs MoonshotAI: Kimi K2.6	`anthropic/claude-opus-4-7`	1	`moonshotai/kimi-k2.6`	27
anthropic/claude-opus-4-8 vs Google: Gemma 4 31B	`anthropic/claude-opus-4-8`	1	`google/gemma-4-31b-it`	26
Claude Opus 4.6 AWS vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-opus-4.6-aws`	0	`deepseek/deepseek-v4-pro`	26
Claude Opus 4.6 Coding vs MiniMax: MiniMax M3	`anthropic/claude-opus-4.6-coding`	0	`minimax/minimax-m3`	25
Claude Opus 4.7 AWS vs Z.ai: GLM 5.3	`anthropic/claude-opus-4.7-aws`	0	`z-ai/glm-5.3`	50
Claude Opus 4.7 Coding vs Z.ai: GLM 5.2	`anthropic/claude-opus-4.7-coding`	0	`z-ai/glm-5.2`	48
Claude Opus 4.8 AWS vs Z.ai: GLM 5.3 Flash	`anthropic/claude-opus-4.8-aws`	0	`z-ai/glm-5.3-flash`	48
Claude Opus 4.8 Coding vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4.8-coding`	0	`moonshotai/kimi-k3`	45
anthropic/claude-opus-5-5 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-opus-5-5`	1	`deepseek/deepseek-v4-flash-0731`	35
Claude Opus 5 AWS vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-opus-5-aws`	0	`deepseek/deepseek-v4.1-flash`	37
anthropic/claude-sonnet-4-6 vs OpenAI: gpt-oss-120b	`anthropic/claude-sonnet-4-6`	1	`openai/gpt-oss-120b`	37
anthropic/claude-sonnet-5-5 vs Qwen: Qwen3.8 27B	`anthropic/claude-sonnet-5-5`	1	`qwen/qwen3.8-27b`	30
Claude Sonnet 5 AWS vs MoonshotAI: Kimi K2.6	`anthropic/claude-sonnet-5-aws`	0	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs OpenAI: GPT-5 Pro	`google/gemma-4-31b-it`	26	`openai/gpt-5-pro`	1
DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: GPT-5.2 Pro	`deepseek/deepseek-v4-pro`	26	`openai/gpt-5.2-pro`	1
MiniMax: MiniMax M3 vs OpenAI: GPT-5.3-Codex	`minimax/minimax-m3`	25	`openai/gpt-5.3-codex`	1
OpenAI: GPT-5.4 Nano vs Z.ai: GLM 5.3	`openai/gpt-5.4-nano`	2	`z-ai/glm-5.3`	50
InclusionAI: Ling-3.0-flash-fin vs Z.ai: GLM 5.2	`inclusionai/ling-3.0-flash-fin`	1	`z-ai/glm-5.2`	48
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-235b-a22b-instruct-2507-fp8`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3 Next 80B A3B Thinking	`moonshotai/kimi-k3`	45	`qwen/qwen3-next-80b-a3b-thinking`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.8 Max 0902	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3.8-max-0902`	1
DeepSeek: DeepSeek V4.1 Flash vs Tencent: Hy3 preview	`deepseek/deepseek-v4.1-flash`	37	`tencent/hy3-preview`	1
OpenAI: gpt-oss-120b vs TrustedRouter Gemmev 1.0	`openai/gpt-oss-120b`	37	`trustedrouter/gemmev-1.0`	0
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8 vs Qwen: Qwen3.8 27B	`qwen/qwen3-235b-a22b-thinking-2507-fp8`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8	`moonshotai/kimi-k2.6`	27	`qwen/qwen3-coder-480b-a35b-instruct-fp8`	1
Google: Gemma 4 31B vs Proxy: zai-org/GLM-4.7	`google/gemma-4-31b-it`	26	`z-ai/glm-4.7-fp8`	1
anthropic/claude-haiku-4-5 vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-haiku-4-5`	1	`deepseek/deepseek-v4-pro`	26
Claude Haiku 4.5 20251001 vs MiniMax: MiniMax M3	`anthropic/claude-haiku-4.5-20251001`	0	`minimax/minimax-m3`	25
Claude Haiku 4.5 20251001 AWS vs Z.ai: GLM 5.3	`anthropic/claude-haiku-4.5-20251001-aws`	0	`z-ai/glm-5.3`	50
Claude Haiku 4.5 20251001 Coding vs Z.ai: GLM 5.2	`anthropic/claude-haiku-4.5-20251001-coding`	0	`z-ai/glm-5.2`	48
Claude Opus 4 20250514 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-opus-4-20250514`	0	`z-ai/glm-5.3-flash`	48
Claude Opus 4 20250514 Coding vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4-20250514-coding`	0	`moonshotai/kimi-k3`	45
Claude Opus 4.1 20250805 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-opus-4.1-20250805`	0	`deepseek/deepseek-v4-flash-0731`	35
Claude Opus 4.1 20250805 Coding vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-opus-4.1-20250805-coding`	0	`deepseek/deepseek-v4.1-flash`	37
Claude Opus 4.5 20251101 vs OpenAI: gpt-oss-120b	`anthropic/claude-opus-4.5-20251101`	0	`openai/gpt-oss-120b`	37
Claude Opus 4.5 20251101 Coding vs Qwen: Qwen3.8 27B	`anthropic/claude-opus-4.5-20251101-coding`	0	`qwen/qwen3.8-27b`	30
Claude Sonnet 4 20250514 Coding vs MoonshotAI: Kimi K2.6	`anthropic/claude-sonnet-4-20250514-coding`	0	`moonshotai/kimi-k2.6`	27