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
DeepSeek V4 Pro 0423 vs Z.ai: GLM 4.7 Flash	`deepseek/deepseek-v4-pro-0423`	4	`z-ai/glm-4.7-flash`	6
Google: Gemini 2.5 Flash vs Z.ai: GLM 4.7 Flash	`google/gemini-2.5-flash`	6	`z-ai/glm-4.7-flash`	6
Google: Gemini 3.1 Flash Lite vs Z.ai: GLM 4.7 Flash	`google/gemini-3.1-flash-lite`	6	`z-ai/glm-4.7-flash`	6
Xiaomi: MiMo-V2.5 vs Z.ai: GLM 4.7 Flash	`xiaomi/mimo-v2.5`	5	`z-ai/glm-4.7-flash`	6
OpenAI: GPT-5.5 vs Z.ai: GLM 5.2	`openai/gpt-5.5`	4	`z-ai/glm-5.2`	48
OpenAI: GPT-5.6 Terra vs Z.ai: GLM 5.3 Flash	`openai/gpt-5.6-terra`	4	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs OpenAI: GPT-6 Astra	`moonshotai/kimi-k3`	45	`openai/gpt-6-astra`	4
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-6 Luna	`deepseek/deepseek-v4-flash-0731`	35	`openai/gpt-6-luna`	4
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-6 Sol	`deepseek/deepseek-v4.1-flash`	37	`openai/gpt-6-sol`	4
Google: Gemini 2.5 Flash Lite vs OpenAI: gpt-oss-120b	`google/gemini-2.5-flash-lite`	2	`openai/gpt-oss-120b`	37
Google: Gemini 3 Flash Preview vs Qwen: Qwen3.8 27B	`google/gemini-3-flash-preview`	3	`qwen/qwen3.8-27b`	30
Google: Gemini 3.5 Flash vs MoonshotAI: Kimi K2.6	`google/gemini-3.5-flash`	3	`moonshotai/kimi-k2.6`	27
Google: Gemini 3.5 Flash Lite vs Google: Gemma 4 31B	`google/gemini-3.5-flash-lite`	4	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemini 3.6 Flash	`deepseek/deepseek-v4-pro`	26	`google/gemini-3.6-flash`	4
Google: Gemini 3.7 Flash vs MiniMax: MiniMax M3	`google/gemini-3.7-flash`	4	`minimax/minimax-m3`	25
Google: Gemini 4 Argon vs Z.ai: GLM 5.3	`google/gemini-4-argon`	4	`z-ai/glm-5.3`	50
Llama 4 Maverick Instruct vs Z.ai: GLM 5.2	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8`	3	`z-ai/glm-5.2`	48
Muse Spark Open vs Z.ai: GLM 5.3 Flash	`meta-models/muse-spark-open`	4	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Nemotron Super 3.5	`moonshotai/kimi-k3`	45	`nvidia/nemotron-3.5-super-vl-120b-a12b`	3
DeepSeek: DeepSeek V4 Flash 0731 vs StepFun: Step 5 Preview	`deepseek/deepseek-v4-flash-0731`	35	`stepfun/step-5-preview`	4
DeepSeek: DeepSeek V4.1 Flash vs GLM 5.3 Fast on Fireworks	`deepseek/deepseek-v4.1-flash`	37	`z-ai/glm-5.3-fast`	4
OpenAI: gpt-oss-120b vs Z.ai: GLM 5.3 FlashX	`openai/gpt-oss-120b`	37	`z-ai/glm-5.3-flashx`	4
OpenAI: GPT-4.1 Mini vs Qwen: Qwen3.8 27B	`openai/gpt-4.1-mini`	3	`qwen/qwen3.8-27b`	30
Anthropic: Claude Sonnet 4.6 vs MoonshotAI: Kimi K2.6	`anthropic/claude-sonnet-4.6`	3	`moonshotai/kimi-k2.6`	27
DeepSeek V4 Flash 0731 Fast vs Google: Gemma 4 31B	`deepseek/deepseek-v4-flash-0731-fast`	4	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3.5 Flash	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3.5-flash`	2
MiniMax: MiniMax M3 vs Qwen3.5 Plus	`minimax/minimax-m3`	25	`qwen/qwen3.5-plus`	2
Qwen3.7 Plus vs Z.ai: GLM 5.3	`qwen/qwen3.7-plus`	2	`z-ai/glm-5.3`	50
SpaceXAI: Grok 4.3 vs Z.ai: GLM 5.2	`x-ai/grok-4.3`	3	`z-ai/glm-5.2`	48
Thinking Machines: Inkling Small vs Z.ai: GLM 5.3 Flash	`thinkingmachines/inkling-small`	4	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs SpaceXAI: Grok 4.5	`moonshotai/kimi-k3`	45	`x-ai/grok-4.5`	3
DeepSeek: DeepSeek V4 Flash 0731 vs SpaceXAI: Grok 4.6	`deepseek/deepseek-v4-flash-0731`	35	`x-ai/grok-4.6`	3
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-5 Mini	`deepseek/deepseek-v4.1-flash`	37	`openai/gpt-5-mini`	3
OpenAI: GPT-5.4 Mini vs OpenAI: gpt-oss-120b	`openai/gpt-5.4-mini`	4	`openai/gpt-oss-120b`	37
inclusionAI: Ling 3.0 Flash vs Qwen: Qwen3.8 27B	`inclusionai/ling-3.0-flash`	4	`qwen/qwen3.8-27b`	30
Mistral: Mistral Small 4 vs MoonshotAI: Kimi K2.6	`mistralai/mistral-small-2603`	4	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs MoonshotAI: Kimi K2 Thinking	`google/gemma-4-31b-it`	26	`moonshotai/kimi-k2-thinking`	4
DeepSeek: DeepSeek V4 Pro 0423 vs moonshotai/Kimi: K2.7-Code-Highspeed	`deepseek/deepseek-v4-pro`	26	`moonshotai/kimi-k2.7-code-highspeed`	5
MiniMax: MiniMax M3 vs NVIDIA: Nemotron 3 Nano 30B A3B	`minimax/minimax-m3`	25	`nvidia/nemotron-3-nano-30b-a3b`	4
NVIDIA: Nemotron 3.5 Super VL vs Z.ai: GLM 5.3	`nvidia/nemotron-3.5-super-vl`	4	`z-ai/glm-5.3`	50
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo vs Z.ai: GLM 5.2	`qwen/qwen3-coder-480b-a35b-instruct-turbo`	4	`z-ai/glm-5.2`	48
Qwen: Qwen3 Coder Next vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-coder-next`	3	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3.6 Plus	`moonshotai/kimi-k3`	45	`qwen/qwen3.6-plus`	3
DeepSeek: DeepSeek V4 Flash 0731 vs StepFun: Step 3.7 Flash	`deepseek/deepseek-v4-flash-0731`	35	`stepfun/step-3.7-flash`	3
DeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok Build 0.1	`deepseek/deepseek-v4.1-flash`	37	`x-ai/grok-build-0.1`	3
deepseek-ai/DeepSeek-V3 vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v3`	3	`openai/gpt-oss-120b`	37
IBM: Granite 4.2 8B vs Qwen: Qwen3.8 27B	`ibm-granite/granite-4.2-8b`	3	`qwen/qwen3.8-27b`	30
Meta: Llama 3.1 70B Instruct vs MoonshotAI: Kimi K2.6	`meta-llama/llama-3.1-70b-instruct`	4	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs meta-models/Muse-Glimmer-30B	`google/gemma-4-31b-it`	26	`meta-models/muse-glimmer-30b`	4
DeepSeek: DeepSeek V4 Pro 0423 vs Mistral: Mistral Nemo	`deepseek/deepseek-v4-pro`	26	`mistralai/mistral-nemo`	4
MiniMax: MiniMax M3 vs mistralai/Mistral-Nemo-Instruct-2407	`minimax/minimax-m3`	25	`mistralai/mistral-nemo-instruct-2407`	3
Nemotron-3-Nano-Omni-30B vs Z.ai: GLM 5.3	`nvidia/nemotron-3-nano-omni`	4	`z-ai/glm-5.3`	50
Qwen: Qwen3 VL 235B A22B Instruct vs Z.ai: GLM 5.2	`qwen/qwen3-vl-235b-a22b-instruct`	4	`z-ai/glm-5.2`	48
Qwen: Qwen3 VL 235B A22B Thinking vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-235b-a22b-thinking`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen: Qwen3 VL 30B A3B Instruct	`moonshotai/kimi-k3`	45	`qwen/qwen3-vl-30b-a3b-instruct`	4
DeepSeek: DeepSeek V4 Flash 0731 vs @cf/meta/llama-3.2-11b-vision-instruct	`deepseek/deepseek-v4-flash-0731`	35	`meta-llama/llama-3.2-11b-vision-instruct`	2
DeepSeek: DeepSeek V4.1 Flash vs mistralai/Mistral-Small-3.2-24B-Instruct-2506	`deepseek/deepseek-v4.1-flash`	37	`mistralai/mistral-small-3.2-24b-instruct-2506`	3
OpenAI: gpt-oss-120b vs Qwen: Qwen3 30B A3B	`openai/gpt-oss-120b`	37	`qwen/qwen3-30b-a3b`	3
@cf/qwen/qwen2.5-coder-32b-instruct vs Qwen: Qwen3.8 27B	`qwen/qwen2.5-coder-32b-instruct`	2	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen3-235B-A22B	`moonshotai/kimi-k2.6`	27	`qwen/qwen3-235b-a22b`	3
Google: Gemma 4 31B vs Qwen3 Embedding 8B	`google/gemma-4-31b-it`	26	`qwen/qwen3-embedding-8b`	2
DeepSeek: DeepSeek V4 Pro 0423 vs TypeSafe AI Jev	`deepseek/deepseek-v4-pro`	26	`typesafe-ai/jev`	2
MiniMax: MiniMax M3 vs Qwen MT Plus	`minimax/minimax-m3`	25	`qwen/qwen-mt-plus`	3
ByteDance Seedance 2.5 vs Z.ai: GLM 5.3	`bytedance/seedance-2.5`	2	`z-ai/glm-5.3`	50
ByteDance Seedance 2.0 vs Z.ai: GLM 5.2	`bytedance/seedance-2.0`	2	`z-ai/glm-5.2`	48
ByteDance Seedance 2.0 Fast vs Z.ai: GLM 5.3 Flash	`bytedance/seedance-2.0-fast`	2	`z-ai/glm-5.3-flash`	48
MythoMax 13B vs MoonshotAI: Kimi K3	`gryphe/mythomax-l2-13b`	4	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax Hailuo 3 (H3)	`deepseek/deepseek-v4-flash-0731`	35	`minimax/hailuo-3`	2
DeepSeek: DeepSeek V4.1 Flash vs remm-slerp:l2-13b	`deepseek/deepseek-v4.1-flash`	37	`undi95/remm-slerp-l2-13b`	2
Alibaba Wan 2.7 vs OpenAI: gpt-oss-120b	`alibaba/wan-2.7`	2	`openai/gpt-oss-120b`	37
Lightricks LTX 2.3 vs Qwen: Qwen3.8 27B	`lightricks/ltx-2.3`	2	`qwen/qwen3.8-27b`	30
Lightricks LTX 2.3 Fast vs MoonshotAI: Kimi K2.6	`lightricks/ltx-2.3-fast`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs Kling Video 3.0 Omni Pro	`google/gemma-4-31b-it`	26	`kling/o3-pro`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Kling Video 3.0 Pro	`deepseek/deepseek-v4-pro`	26	`kling/v3-pro`	2
Google Veo 3.1 vs MiniMax: MiniMax M3	`google/veo-3.1`	2	`minimax/minimax-m3`	25
Google Veo 3.1 Fast vs Z.ai: GLM 5.3	`google/veo-3.1-fast`	2	`z-ai/glm-5.3`	50
OpenAI Sora 2 vs Z.ai: GLM 5.2	`openai/sora-2`	2	`z-ai/glm-5.2`	48
OpenAI Sora 2 Pro vs Z.ai: GLM 5.3 Flash	`openai/sora-2-pro`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Runway Gen-4.5	`moonshotai/kimi-k3`	45	`runway/gen-4.5`	2
DeepSeek: DeepSeek V4 Flash 0731 vs grok-4.20-0309-reasoning	`deepseek/deepseek-v4-flash-0731`	35	`x-ai/grok-4.20-reasoning`	3
DeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok 4.20	`deepseek/deepseek-v4.1-flash`	37	`x-ai/grok-4.20`	2
GPT 5.6 Luna vs OpenAI: gpt-oss-120b	`openai/gpt-5.6-luna-az`	1	`openai/gpt-oss-120b`	37
GPT 5.6 Sol vs Qwen: Qwen3.8 27B	`openai/gpt-5.6-sol-az`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs GPT 5.6 Sol	`moonshotai/kimi-k2.6`	27	`openai/gpt-5.6-sol-codex`	1
Google: Gemma 4 31B vs GPT 5.6 Terra	`google/gemma-4-31b-it`	26	`openai/gpt-5.6-terra-az`	1
DeepSeek: DeepSeek V4 Pro 0423 vs GPT 6 Sol	`deepseek/deepseek-v4-pro`	26	`openai/gpt-6-sol-codex`	1
MiniMax: MiniMax M3 vs OpenAI: GPT-6.1 Sol	`minimax/minimax-m3`	25	`openai/gpt-6.1-sol`	3
LongCat 2.0 vs Z.ai: GLM 5.3	`meituan-longcat/longcat-2.0`	1	`z-ai/glm-5.3`	50
DeepSeek V4 Pro vs Z.ai: GLM 5.2	`deepseek-ai/DeepSeek-V4-Pro`	2	`z-ai/glm-5.2`	48
DeepSeek V4.1 Flash (rolling) vs Z.ai: GLM 5.3 Flash	`deepseek/deepseek-flash`	2	`z-ai/glm-5.3-flash`	48
DeepSeek-V4-Flash-0423 vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4-flash-0423`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs deepseek/deepseek-v4-flash-0731-p	`deepseek/deepseek-v4-flash-0731`	35	`deepseek/deepseek-v4-flash-0731-p`	2
DeepSeek V4 Pro 0813 vs DeepSeek: DeepSeek V4.1 Flash	`deepseek/deepseek-v4-pro-0813`	1	`deepseek/deepseek-v4.1-flash`	37
deepseek/deepseek-v4-pro-0813-p vs OpenAI: gpt-oss-120b	`deepseek/deepseek-v4-pro-0813-p`	2	`openai/gpt-oss-120b`	37
DeepSeek V4.1 Flash 1017 Fast vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4.1-flash-1017-fast`	2	`qwen/qwen3.8-27b`	30
DeepSeek V4.1 Flash DST vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4.1-flash-dst`	2	`moonshotai/kimi-k2.6`	27
DeepSeek V4.1 Flash Fast vs Google: Gemma 4 31B	`deepseek/deepseek-v4.1-flash-fast`	2	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs DeepSeek V4.1 Flash	`deepseek/deepseek-v4-pro`	26	`deepseek/deepseek-v4.1-flash-p`	2
Deepseek V4P1 Flash on Fireworks vs MiniMax: MiniMax M3	`deepseek/deepseek-v4p1-flash`	2	`minimax/minimax-m3`	25
Deepseek V4P1 Flash 1017 on Fireworks vs Z.ai: GLM 5.3	`deepseek/deepseek-v4p1-flash-1017`	2	`z-ai/glm-5.3`	50