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
Claude Opus 4.5 vs DeepSeek: DeepSeek V4 Flash 0731 anthropic/claude-opus-4-5-20251101 1 deepseek/deepseek-v4-flash-0731 33
Claude Opus 4.6 vs MoonshotAI: Kimi K3 anthropic/claude-opus-4-6 1 moonshotai/kimi-k3 39
Claude Opus 4.1 20250805 vs OpenAI: gpt-oss-120b anthropic/claude-opus-4.1-20250805 0 openai/gpt-oss-120b 36
Claude Opus 4.1 20250805 Coding vs MoonshotAI: Kimi K2.6 anthropic/claude-opus-4.1-20250805-coding 0 moonshotai/kimi-k2.6 33
Claude Opus 4.5 20251101 vs DeepSeek: DeepSeek V4 Flash 0423 anthropic/claude-opus-4.5-20251101 0 deepseek/deepseek-v4-flash 25
Claude Opus 4.5 20251101 Coding vs DeepSeek: DeepSeek V4 Pro 0423 anthropic/claude-opus-4.5-20251101-coding 0 deepseek/deepseek-v4-pro 26
Claude Sonnet 4 20250514 Coding vs Google: Gemma 4 31B anthropic/claude-sonnet-4-20250514-coding 0 google/gemma-4-31b-it 25
Claude Sonnet 4.5 vs DeepSeek: DeepSeek V4.1 Flash anthropic/claude-sonnet-4-5-20250929 1 deepseek/deepseek-v4.1-flash 23
Claude Sonnet 4.5 20250929 vs MoonshotAI: Kimi K2.7 Code anthropic/claude-sonnet-4.5-20250929 0 moonshotai/kimi-k2.7-code 19
Claude Sonnet 4.5 20250929 Coding vs Z.ai: GLM 5.2 anthropic/claude-sonnet-4.5-20250929-coding 0 z-ai/glm-5.2 44
Claude Sonnet 4.6 AWS vs Z.ai: GLM 5.3 anthropic/claude-sonnet-4.6-aws 0 z-ai/glm-5.3 43
Claude Sonnet 4.6 Coding vs Z.ai: GLM 5.3 Flash anthropic/claude-sonnet-4.6-coding 0 z-ai/glm-5.3-flash 41
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: o1-pro deepseek/deepseek-v4-flash-0731 33 openai/o1-pro 1
MoonshotAI: Kimi K3 vs OpenAI: o3 Pro moonshotai/kimi-k3 39 openai/o3-pro 1
DeepSeek R1 Distill Qwen3 8B 0528 vs OpenAI: gpt-oss-120b deepseek/deepseek-r1-0528-qwen3-8b 1 openai/gpt-oss-120b 36
Meta Llama 3.1 8B Instruct vs MoonshotAI: Kimi K2.6 meta-llama/Meta-Llama-3.1-8B-Instruct 1 moonshotai/kimi-k2.6 33
DeepSeek: DeepSeek V4 Flash 0423 vs nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 deepseek/deepseek-v4-flash 25 nvidia/nemotron-3.5-lightning-30b-a3b-bf16 1
DeepSeek: DeepSeek V4 Pro 0423 vs PaddleOCR VL deepseek/deepseek-v4-pro 26 paddlepaddle/paddleocr-vl 1
gemma 2 2b it vs Google: Gemma 4 31B google/gemma-2-2b-it 1 google/gemma-4-31b-it 25
DeepSeek: DeepSeek V4.1 Flash vs Hermes 2 Pro Llama 3 8B deepseek/deepseek-v4.1-flash 23 nousresearch/hermes-2-pro-llama-3-8b 1
MoonshotAI: Kimi K2.7 Code vs Llama 3 70B Euryale V2.1 moonshotai/kimi-k2.7-code 19 sao10k/l3-70b-euryale-v2.1 1
OpenAI: GPT-3.5 Turbo Instruct vs Z.ai: GLM 5.2 openai/gpt-3.5-turbo-instruct 1 z-ai/glm-5.2 44
Multilingual E5 Large Instruct vs Z.ai: GLM 5.3 intfloat/multilingual-e5-large-instruct 0 z-ai/glm-5.3 43
Qwen: Qwen3.5-27B vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3.5-27b 6 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3.8 2.4T A95B vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3.8-2.4t-a95b 8 xiaomi/mimo-v2.5-pro 8
Tencent: Hy3 vs Xiaomi: MiMo-V2.5-Pro tencent/hy3 8 xiaomi/mimo-v2.5-pro 8
Google: Gemma 3 27B vs Xiaomi: MiMo-V2.5-Pro google/gemma-3-27b-it 8 xiaomi/mimo-v2.5-pro 8
Meta: Llama 3.1 8B Instruct vs Xiaomi: MiMo-V2.5-Pro meta-llama/llama-3.1-8b-instruct 6 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 235B A22B Thinking 2507 vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-235b-a22b-thinking-2507 7 xiaomi/mimo-v2.5-pro 8
OpenAI: GPT-5.6 Terra vs Xiaomi: MiMo-V2.5-Pro openai/gpt-5.6-terra 6 xiaomi/mimo-v2.5-pro 8
OpenAI: GPT-6 Astra vs Xiaomi: MiMo-V2.5-Pro openai/gpt-6-astra 6 xiaomi/mimo-v2.5-pro 8
Llama 4 Maverick Instruct vs Xiaomi: MiMo-V2.5-Pro meta-llama/llama-4-maverick-17b-128e-instruct-fp8 5 xiaomi/mimo-v2.5-pro 8
NVIDIA: Nemotron 3 Nano 30B A3B vs Xiaomi: MiMo-V2.5-Pro nvidia/nemotron-3-nano-30b-a3b 6 xiaomi/mimo-v2.5-pro 8
nvidia/Nemotron-3.5-Lightning-30B-A3B vs Xiaomi: MiMo-V2.5-Pro nvidia/nemotron-3.5-lightning-30b-a3b 4 xiaomi/mimo-v2.5-pro 8
Qwen3 Max vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-max 5 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 VL 30B A3B Instruct vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-vl-30b-a3b-instruct 5 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 VL 8B Instruct vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-vl-8b-instruct 4 xiaomi/mimo-v2.5-pro 8
Xiaomi: MiMo-V2.5-Pro vs Z.ai: GLM 5V Turbo xiaomi/mimo-v2.5-pro 8 z-ai/glm-5v-turbo 5
DeepSeek: R1 0528 vs Xiaomi: MiMo-V2.5-Pro deepseek/deepseek-r1-0528 6 xiaomi/mimo-v2.5-pro 8
Qwen: Qwen3 Coder 30B A3B Instruct vs Xiaomi: MiMo-V2.5-Pro qwen/qwen3-coder-30b-a3b-instruct 4 xiaomi/mimo-v2.5-pro 8
Google: Gemma 3 12B vs Xiaomi: MiMo-V2.5-Pro google/gemma-3-12b-it 5 xiaomi/mimo-v2.5-pro 8
Meta: Llama 3.1 70B Instruct vs Xiaomi: MiMo-V2.5-Pro meta-llama/llama-3.1-70b-instruct 5 xiaomi/mimo-v2.5-pro 8
Llama 4 Scout Instruct vs Xiaomi: MiMo-V2.5-Pro meta-llama/llama-4-scout-17b-16e-instruct 5 xiaomi/mimo-v2.5-pro 8
Muse Glimmer 30B on Fireworks vs Xiaomi: MiMo-V2.5-Pro meta-models/muse-glimmer-30b 6 xiaomi/mimo-v2.5-pro 8
DeepSeek V4 Pro 0423 vs Google: Gemini 2.5 Pro deepseek/deepseek-v4-pro-0423 4 google/gemini-2.5-pro 6
DeepSeek V4 Pro 0423 vs Google: Gemini 3 Flash Preview deepseek/deepseek-v4-pro-0423 4 google/gemini-3-flash-preview 6
DeepSeek V4 Pro 0423 vs Google: Gemini 3.1 Flash Lite deepseek/deepseek-v4-pro-0423 4 google/gemini-3.1-flash-lite 6
DeepSeek V4 Pro 0423 vs Google: Gemini 3.1 Pro Preview deepseek/deepseek-v4-pro-0423 4 google/gemini-3.1-pro-preview 7
DeepSeek V4 Pro 0423 vs Google: Gemini 3.5 Flash deepseek/deepseek-v4-pro-0423 4 google/gemini-3.5-flash 7
DeepSeek V4 Pro 0423 vs Qwen3.7 Max deepseek/deepseek-v4-pro-0423 4 qwen/qwen3.7-max 7
DeepSeek V4 Pro 0423 vs Qwen3.8 Max deepseek/deepseek-v4-pro-0423 4 qwen/qwen3.8-max 8
DeepSeek V4 Pro 0423 vs Thinking Machines: Inkling deepseek/deepseek-v4-pro-0423 4 thinkingmachines/inkling 7
DeepSeek V4 Pro 0423 vs Thinking Machines: Inkling Small deepseek/deepseek-v4-pro-0423 4 thinkingmachines/inkling-small 7
DeepSeek V4 Pro 0423 vs NVIDIA: Nemotron 3 Super deepseek/deepseek-v4-pro-0423 4 nvidia/nemotron-3-super-120b-a12b 7
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 Coder Next deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-coder-next 7
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 VL 235B A22B Instruct deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-vl-235b-a22b-instruct 7
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.5-27B deepseek/deepseek-v4-pro-0423 4 qwen/qwen3.5-27b 6
DeepSeek V4 Pro 0423 vs Qwen: Qwen3.8 2.4T A95B deepseek/deepseek-v4-pro-0423 4 qwen/qwen3.8-2.4t-a95b 8
DeepSeek V4 Pro 0423 vs Tencent: Hy3 deepseek/deepseek-v4-pro-0423 4 tencent/hy3 8
DeepSeek V4 Pro 0423 vs Google: Gemma 3 27B deepseek/deepseek-v4-pro-0423 4 google/gemma-3-27b-it 8
DeepSeek V4 Pro 0423 vs Meta: Llama 3.1 8B Instruct deepseek/deepseek-v4-pro-0423 4 meta-llama/llama-3.1-8b-instruct 6
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 235B A22B Thinking 2507 deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-235b-a22b-thinking-2507 7
DeepSeek V4 Pro 0423 vs OpenAI: GPT-5.6 Terra deepseek/deepseek-v4-pro-0423 4 openai/gpt-5.6-terra 6
DeepSeek V4 Pro 0423 vs OpenAI: GPT-6 Astra deepseek/deepseek-v4-pro-0423 4 openai/gpt-6-astra 6
DeepSeek V4 Pro 0423 vs Llama 4 Maverick Instruct deepseek/deepseek-v4-pro-0423 4 meta-llama/llama-4-maverick-17b-128e-instruct-fp8 5
DeepSeek V4 Pro 0423 vs NVIDIA: Nemotron 3 Nano 30B A3B deepseek/deepseek-v4-pro-0423 4 nvidia/nemotron-3-nano-30b-a3b 6
DeepSeek V4 Pro 0423 vs nvidia/Nemotron-3.5-Lightning-30B-A3B deepseek/deepseek-v4-pro-0423 4 nvidia/nemotron-3.5-lightning-30b-a3b 4
DeepSeek V4 Pro 0423 vs Qwen3 Max deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-max 5
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 VL 30B A3B Instruct deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-vl-30b-a3b-instruct 5
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 VL 8B Instruct deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-vl-8b-instruct 4
DeepSeek V4 Pro 0423 vs Z.ai: GLM 5V Turbo deepseek/deepseek-v4-pro-0423 4 z-ai/glm-5v-turbo 5
DeepSeek: R1 0528 vs DeepSeek V4 Pro 0423 deepseek/deepseek-r1-0528 6 deepseek/deepseek-v4-pro-0423 4
DeepSeek V4 Pro 0423 vs Qwen: Qwen3 Coder 30B A3B Instruct deepseek/deepseek-v4-pro-0423 4 qwen/qwen3-coder-30b-a3b-instruct 4
DeepSeek V4 Pro 0423 vs Google: Gemma 3 12B deepseek/deepseek-v4-pro-0423 4 google/gemma-3-12b-it 5
DeepSeek V4 Pro 0423 vs Meta: Llama 3.1 70B Instruct deepseek/deepseek-v4-pro-0423 4 meta-llama/llama-3.1-70b-instruct 5
DeepSeek V4 Pro 0423 vs Llama 4 Scout Instruct deepseek/deepseek-v4-pro-0423 4 meta-llama/llama-4-scout-17b-16e-instruct 5
DeepSeek V4 Pro 0423 vs Muse Glimmer 30B on Fireworks deepseek/deepseek-v4-pro-0423 4 meta-models/muse-glimmer-30b 6
Google: Gemini 2.5 Pro vs Google: Gemini 3 Flash Preview google/gemini-2.5-pro 6 google/gemini-3-flash-preview 6
Google: Gemini 2.5 Pro vs Google: Gemini 3.1 Flash Lite google/gemini-2.5-pro 6 google/gemini-3.1-flash-lite 6
Google: Gemini 2.5 Pro vs Google: Gemini 3.1 Pro Preview google/gemini-2.5-pro 6 google/gemini-3.1-pro-preview 7
Google: Gemini 2.5 Pro vs Google: Gemini 3.5 Flash google/gemini-2.5-pro 6 google/gemini-3.5-flash 7
Google: Gemini 2.5 Pro vs Qwen3.7 Max google/gemini-2.5-pro 6 qwen/qwen3.7-max 7
Google: Gemini 2.5 Pro vs Qwen3.8 Max google/gemini-2.5-pro 6 qwen/qwen3.8-max 8
Google: Gemini 2.5 Pro vs Thinking Machines: Inkling google/gemini-2.5-pro 6 thinkingmachines/inkling 7
Google: Gemini 2.5 Pro vs Thinking Machines: Inkling Small google/gemini-2.5-pro 6 thinkingmachines/inkling-small 7
Google: Gemini 2.5 Pro vs NVIDIA: Nemotron 3 Super google/gemini-2.5-pro 6 nvidia/nemotron-3-super-120b-a12b 7
Google: Gemini 2.5 Pro vs Qwen: Qwen3 Coder Next google/gemini-2.5-pro 6 qwen/qwen3-coder-next 7
Google: Gemini 2.5 Pro vs Qwen: Qwen3 VL 235B A22B Instruct google/gemini-2.5-pro 6 qwen/qwen3-vl-235b-a22b-instruct 7
Google: Gemini 2.5 Pro vs Qwen: Qwen3.5-27B google/gemini-2.5-pro 6 qwen/qwen3.5-27b 6
Google: Gemini 2.5 Pro vs Qwen: Qwen3.8 2.4T A95B google/gemini-2.5-pro 6 qwen/qwen3.8-2.4t-a95b 8
Google: Gemini 2.5 Pro vs Tencent: Hy3 google/gemini-2.5-pro 6 tencent/hy3 8
Google: Gemini 2.5 Pro vs Google: Gemma 3 27B google/gemini-2.5-pro 6 google/gemma-3-27b-it 8
Google: Gemini 2.5 Pro vs Meta: Llama 3.1 8B Instruct google/gemini-2.5-pro 6 meta-llama/llama-3.1-8b-instruct 6
Google: Gemini 2.5 Pro vs Qwen: Qwen3 235B A22B Thinking 2507 google/gemini-2.5-pro 6 qwen/qwen3-235b-a22b-thinking-2507 7
Google: Gemini 2.5 Pro vs OpenAI: GPT-5.6 Terra google/gemini-2.5-pro 6 openai/gpt-5.6-terra 6
Google: Gemini 2.5 Pro vs OpenAI: GPT-6 Astra google/gemini-2.5-pro 6 openai/gpt-6-astra 6
Google: Gemini 2.5 Pro vs Llama 4 Maverick Instruct google/gemini-2.5-pro 6 meta-llama/llama-4-maverick-17b-128e-instruct-fp8 5
Google: Gemini 2.5 Pro vs NVIDIA: Nemotron 3 Nano 30B A3B google/gemini-2.5-pro 6 nvidia/nemotron-3-nano-30b-a3b 6
Google: Gemini 2.5 Pro vs nvidia/Nemotron-3.5-Lightning-30B-A3B google/gemini-2.5-pro 6 nvidia/nemotron-3.5-lightning-30b-a3b 4
Google: Gemini 2.5 Pro vs Qwen3 Max google/gemini-2.5-pro 6 qwen/qwen3-max 5
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

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