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.
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 5 vs Thinking Machines: Inkling anthropic/claude-opus-5 5 thinkingmachines/inkling 6
Qwen: Qwen3 Coder Next vs Thinking Machines: Inkling qwen/qwen3-coder-next 5 thinkingmachines/inkling 6
Qwen: Qwen3 VL 30B A3B Instruct vs Thinking Machines: Inkling qwen/qwen3-vl-30b-a3b-instruct 5 thinkingmachines/inkling 6
Thinking Machines: Inkling vs Z.ai: GLM 5 Turbo thinkingmachines/inkling 6 z-ai/glm-5-turbo 5
DeepSeek: R1 0528 vs Thinking Machines: Inkling deepseek/deepseek-r1-0528 5 thinkingmachines/inkling 6
DeepSeek: DeepSeek V3.2 Exp vs Thinking Machines: Inkling deepseek/deepseek-v3.2-exp 5 thinkingmachines/inkling 6
Qwen: Qwen3 32B vs Thinking Machines: Inkling qwen/qwen3-32b 5 thinkingmachines/inkling 6
OpenAI: GPT-4o vs Thinking Machines: Inkling openai/gpt-4o 5 thinkingmachines/inkling 6
OpenAI: GPT-5.5 vs Thinking Machines: Inkling openai/gpt-5.5 4 thinkingmachines/inkling 6
OpenAI: GPT-5.6 Sol vs Thinking Machines: Inkling openai/gpt-5.6-sol 4 thinkingmachines/inkling 6
Google: Gemini 3.5 Flash Lite vs Thinking Machines: Inkling google/gemini-3.5-flash-lite 4 thinkingmachines/inkling 6
Google: Gemini 3.6 Flash vs Thinking Machines: Inkling google/gemini-3.6-flash 4 thinkingmachines/inkling 6
Meta: Llama 4 Maverick vs Thinking Machines: Inkling meta-llama/llama-4-maverick 4 thinkingmachines/inkling 6
OpenAI: GPT-4.1 vs Thinking Machines: Inkling openai/gpt-4.1 4 thinkingmachines/inkling 6
NVIDIA: Nemotron 3 Super vs Thinking Machines: Inkling nvidia/nemotron-3-super-120b-a12b 4 thinkingmachines/inkling 6
Qwen3.7-Max vs Thinking Machines: Inkling qwen/qwen3.7-max 4 thinkingmachines/inkling 6
OpenAI: GPT-5 Nano vs Thinking Machines: Inkling openai/gpt-5-nano 4 thinkingmachines/inkling 6
OpenAI: GPT-5.4 Mini vs Thinking Machines: Inkling openai/gpt-5.4-mini 4 thinkingmachines/inkling 6
Qwen: Qwen3 VL 8B Instruct vs Thinking Machines: Inkling qwen/qwen3-vl-8b-instruct 4 thinkingmachines/inkling 6
MiniMax: MiniMax M2 vs Thinking Machines: Inkling minimax/minimax-m2 4 thinkingmachines/inkling 6
MiniMax M2.5-highspeed vs Thinking Machines: Inkling minimax/minimax-m2.5-highspeed 4 thinkingmachines/inkling 6
DeepSeek V3 0324 vs Thinking Machines: Inkling deepseek/deepseek-v3-0324 4 thinkingmachines/inkling 6
Thinking Machines: Inkling Small vs GLM 5.2 Fast on Fireworks thinkingmachines/inkling-small 6 z-ai/glm-5.2-fast 6
NVIDIA: Nemotron 3 Nano 30B A3B vs GLM 5.2 Fast on Fireworks nvidia/nemotron-3-nano-30b-a3b 6 z-ai/glm-5.2-fast 6
Qwen: Qwen3 235B A22B Instruct 2507 vs GLM 5.2 Fast on Fireworks qwen/qwen3-235b-a22b-2507 6 z-ai/glm-5.2-fast 6
Z.ai: GLM 4.7 Flash vs GLM 5.2 Fast on Fireworks z-ai/glm-4.7-flash 6 z-ai/glm-5.2-fast 6
Mistral: Mistral Nemo vs GLM 5.2 Fast on Fireworks mistralai/mistral-nemo 6 z-ai/glm-5.2-fast 6
Xiaomi: MiMo-V2.5-Pro vs GLM 5.2 Fast on Fireworks xiaomi/mimo-v2.5-pro 5 z-ai/glm-5.2-fast 6
Claude Opus 5 vs GLM 5.2 Fast on Fireworks anthropic/claude-opus-5 5 z-ai/glm-5.2-fast 6
Qwen: Qwen3 Coder Next vs GLM 5.2 Fast on Fireworks qwen/qwen3-coder-next 5 z-ai/glm-5.2-fast 6
Qwen: Qwen3 VL 30B A3B Instruct vs GLM 5.2 Fast on Fireworks qwen/qwen3-vl-30b-a3b-instruct 5 z-ai/glm-5.2-fast 6
Z.ai: GLM 5 Turbo vs GLM 5.2 Fast on Fireworks z-ai/glm-5-turbo 5 z-ai/glm-5.2-fast 6
DeepSeek: R1 0528 vs GLM 5.2 Fast on Fireworks deepseek/deepseek-r1-0528 5 z-ai/glm-5.2-fast 6
DeepSeek: DeepSeek V3.2 Exp vs GLM 5.2 Fast on Fireworks deepseek/deepseek-v3.2-exp 5 z-ai/glm-5.2-fast 6
Qwen: Qwen3 32B vs GLM 5.2 Fast on Fireworks qwen/qwen3-32b 5 z-ai/glm-5.2-fast 6
OpenAI: GPT-4o vs GLM 5.2 Fast on Fireworks openai/gpt-4o 5 z-ai/glm-5.2-fast 6
OpenAI: GPT-5.5 vs GLM 5.2 Fast on Fireworks openai/gpt-5.5 4 z-ai/glm-5.2-fast 6
OpenAI: GPT-5.6 Sol vs GLM 5.2 Fast on Fireworks openai/gpt-5.6-sol 4 z-ai/glm-5.2-fast 6
Google: Gemini 3.5 Flash Lite vs GLM 5.2 Fast on Fireworks google/gemini-3.5-flash-lite 4 z-ai/glm-5.2-fast 6
Google: Gemini 3.6 Flash vs GLM 5.2 Fast on Fireworks google/gemini-3.6-flash 4 z-ai/glm-5.2-fast 6
Meta: Llama 4 Maverick vs GLM 5.2 Fast on Fireworks meta-llama/llama-4-maverick 4 z-ai/glm-5.2-fast 6
OpenAI: GPT-4.1 vs GLM 5.2 Fast on Fireworks openai/gpt-4.1 4 z-ai/glm-5.2-fast 6
NVIDIA: Nemotron 3 Super vs GLM 5.2 Fast on Fireworks nvidia/nemotron-3-super-120b-a12b 4 z-ai/glm-5.2-fast 6
Qwen3.7-Max vs GLM 5.2 Fast on Fireworks qwen/qwen3.7-max 4 z-ai/glm-5.2-fast 6
OpenAI: GPT-5 Nano vs GLM 5.2 Fast on Fireworks openai/gpt-5-nano 4 z-ai/glm-5.2-fast 6
OpenAI: GPT-5.4 Mini vs GLM 5.2 Fast on Fireworks openai/gpt-5.4-mini 4 z-ai/glm-5.2-fast 6
Qwen: Qwen3 VL 8B Instruct vs GLM 5.2 Fast on Fireworks qwen/qwen3-vl-8b-instruct 4 z-ai/glm-5.2-fast 6
MiniMax: MiniMax M2 vs GLM 5.2 Fast on Fireworks minimax/minimax-m2 4 z-ai/glm-5.2-fast 6
MiniMax M2.5-highspeed vs GLM 5.2 Fast on Fireworks minimax/minimax-m2.5-highspeed 4 z-ai/glm-5.2-fast 6
DeepSeek V3 0324 vs GLM 5.2 Fast on Fireworks deepseek/deepseek-v3-0324 4 z-ai/glm-5.2-fast 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Thinking Machines: Inkling Small nvidia/nemotron-3-nano-30b-a3b 6 thinkingmachines/inkling-small 6
Qwen: Qwen3 235B A22B Instruct 2507 vs Thinking Machines: Inkling Small qwen/qwen3-235b-a22b-2507 6 thinkingmachines/inkling-small 6
Thinking Machines: Inkling Small vs Z.ai: GLM 4.7 Flash thinkingmachines/inkling-small 6 z-ai/glm-4.7-flash 6
Mistral: Mistral Nemo vs Thinking Machines: Inkling Small mistralai/mistral-nemo 6 thinkingmachines/inkling-small 6
Thinking Machines: Inkling Small vs Xiaomi: MiMo-V2.5-Pro thinkingmachines/inkling-small 6 xiaomi/mimo-v2.5-pro 5
Claude Opus 5 vs Thinking Machines: Inkling Small anthropic/claude-opus-5 5 thinkingmachines/inkling-small 6
Qwen: Qwen3 Coder Next vs Thinking Machines: Inkling Small qwen/qwen3-coder-next 5 thinkingmachines/inkling-small 6
Qwen: Qwen3 VL 30B A3B Instruct vs Thinking Machines: Inkling Small qwen/qwen3-vl-30b-a3b-instruct 5 thinkingmachines/inkling-small 6
Thinking Machines: Inkling Small vs Z.ai: GLM 5 Turbo thinkingmachines/inkling-small 6 z-ai/glm-5-turbo 5
DeepSeek: R1 0528 vs Thinking Machines: Inkling Small deepseek/deepseek-r1-0528 5 thinkingmachines/inkling-small 6
DeepSeek: DeepSeek V3.2 Exp vs Thinking Machines: Inkling Small deepseek/deepseek-v3.2-exp 5 thinkingmachines/inkling-small 6
Qwen: Qwen3 32B vs Thinking Machines: Inkling Small qwen/qwen3-32b 5 thinkingmachines/inkling-small 6
OpenAI: GPT-4o vs Thinking Machines: Inkling Small openai/gpt-4o 5 thinkingmachines/inkling-small 6
OpenAI: GPT-5.5 vs Thinking Machines: Inkling Small openai/gpt-5.5 4 thinkingmachines/inkling-small 6
OpenAI: GPT-5.6 Sol vs Thinking Machines: Inkling Small openai/gpt-5.6-sol 4 thinkingmachines/inkling-small 6
Google: Gemini 3.5 Flash Lite vs Thinking Machines: Inkling Small google/gemini-3.5-flash-lite 4 thinkingmachines/inkling-small 6
Google: Gemini 3.6 Flash vs Thinking Machines: Inkling Small google/gemini-3.6-flash 4 thinkingmachines/inkling-small 6
Meta: Llama 4 Maverick vs Thinking Machines: Inkling Small meta-llama/llama-4-maverick 4 thinkingmachines/inkling-small 6
OpenAI: GPT-4.1 vs Thinking Machines: Inkling Small openai/gpt-4.1 4 thinkingmachines/inkling-small 6
NVIDIA: Nemotron 3 Super vs Thinking Machines: Inkling Small nvidia/nemotron-3-super-120b-a12b 4 thinkingmachines/inkling-small 6
Qwen3.7-Max vs Thinking Machines: Inkling Small qwen/qwen3.7-max 4 thinkingmachines/inkling-small 6
OpenAI: GPT-5 Nano vs Thinking Machines: Inkling Small openai/gpt-5-nano 4 thinkingmachines/inkling-small 6
OpenAI: GPT-5.4 Mini vs Thinking Machines: Inkling Small openai/gpt-5.4-mini 4 thinkingmachines/inkling-small 6
Qwen: Qwen3 VL 8B Instruct vs Thinking Machines: Inkling Small qwen/qwen3-vl-8b-instruct 4 thinkingmachines/inkling-small 6
MiniMax: MiniMax M2 vs Thinking Machines: Inkling Small minimax/minimax-m2 4 thinkingmachines/inkling-small 6
MiniMax M2.5-highspeed vs Thinking Machines: Inkling Small minimax/minimax-m2.5-highspeed 4 thinkingmachines/inkling-small 6
DeepSeek V3 0324 vs Thinking Machines: Inkling Small deepseek/deepseek-v3-0324 4 thinkingmachines/inkling-small 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 235B A22B Instruct 2507 nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3-235b-a22b-2507 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Z.ai: GLM 4.7 Flash nvidia/nemotron-3-nano-30b-a3b 6 z-ai/glm-4.7-flash 6
Mistral: Mistral Nemo vs NVIDIA: Nemotron 3 Nano 30B A3B mistralai/mistral-nemo 6 nvidia/nemotron-3-nano-30b-a3b 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Xiaomi: MiMo-V2.5-Pro nvidia/nemotron-3-nano-30b-a3b 6 xiaomi/mimo-v2.5-pro 5
Claude Opus 5 vs NVIDIA: Nemotron 3 Nano 30B A3B anthropic/claude-opus-5 5 nvidia/nemotron-3-nano-30b-a3b 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 Coder Next nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3-coder-next 5
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 VL 30B A3B Instruct nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3-vl-30b-a3b-instruct 5
NVIDIA: Nemotron 3 Nano 30B A3B vs Z.ai: GLM 5 Turbo nvidia/nemotron-3-nano-30b-a3b 6 z-ai/glm-5-turbo 5
DeepSeek: R1 0528 vs NVIDIA: Nemotron 3 Nano 30B A3B deepseek/deepseek-r1-0528 5 nvidia/nemotron-3-nano-30b-a3b 6
DeepSeek: DeepSeek V3.2 Exp vs NVIDIA: Nemotron 3 Nano 30B A3B deepseek/deepseek-v3.2-exp 5 nvidia/nemotron-3-nano-30b-a3b 6
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 32B nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3-32b 5
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-4o nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-4o 5
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-5.5 nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-5.5 4
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-5.6 Sol nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-5.6-sol 4
Google: Gemini 3.5 Flash Lite vs NVIDIA: Nemotron 3 Nano 30B A3B google/gemini-3.5-flash-lite 4 nvidia/nemotron-3-nano-30b-a3b 6
Google: Gemini 3.6 Flash vs NVIDIA: Nemotron 3 Nano 30B A3B google/gemini-3.6-flash 4 nvidia/nemotron-3-nano-30b-a3b 6
Meta: Llama 4 Maverick vs NVIDIA: Nemotron 3 Nano 30B A3B meta-llama/llama-4-maverick 4 nvidia/nemotron-3-nano-30b-a3b 6
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-4.1 nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-4.1 4
NVIDIA: Nemotron 3 Nano 30B A3B vs NVIDIA: Nemotron 3 Super nvidia/nemotron-3-nano-30b-a3b 6 nvidia/nemotron-3-super-120b-a12b 4
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen3.7-Max nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3.7-max 4
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-5 Nano nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-5-nano 4
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-5.4 Mini nvidia/nemotron-3-nano-30b-a3b 6 openai/gpt-5.4-mini 4
NVIDIA: Nemotron 3 Nano 30B A3B vs Qwen: Qwen3 VL 8B Instruct nvidia/nemotron-3-nano-30b-a3b 6 qwen/qwen3-vl-8b-instruct 4
Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

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