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
OpenAI: gpt-oss-120b vs Qwen Plus	`openai/gpt-oss-120b`	38	`qwen/qwen-plus`	1
Qwen Plus 2025 07 28 vs Qwen: Qwen3.8 27B	`qwen/qwen-plus-2025-07-28`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen Plus 2025 09 11	`moonshotai/kimi-k2.6`	27	`qwen/qwen-plus-2025-09-11`	1
Google: Gemma 4 31B vs Qwen Plus 2025 12 01	`google/gemma-4-31b-it`	26	`qwen/qwen-plus-2025-12-01`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3 Coder Flash	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-coder-flash`	1
MiniMax: MiniMax M3 vs Qwen3 Coder Flash 2025 07 28	`minimax/minimax-m3`	25	`qwen/qwen3-coder-flash-2025-07-28`	1
Qwen3.5 Flash 2026 02 23 vs Z.ai: GLM 5.3	`qwen/qwen3.5-flash-2026-02-23`	1	`z-ai/glm-5.3`	50
Qwen3.5 Plus 2026 02 15 vs Z.ai: GLM 5.2	`qwen/qwen3.5-plus-2026-02-15`	1	`z-ai/glm-5.2`	48
Qwen3.6 Flash vs Z.ai: GLM 5.3 Flash	`qwen/qwen3.6-flash`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen3.6 Flash 2026 04 16	`moonshotai/kimi-k3`	45	`qwen/qwen3.6-flash-2026-04-16`	1
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.7 Flash	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen3.7-flash`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen3.7 Flash 2026 07 15	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen3.7-flash-2026-07-15`	1
OpenAI: gpt-oss-120b vs Qwen3.7 Max 2026 05 20	`openai/gpt-oss-120b`	38	`qwen/qwen3.7-max-2026-05-20`	1
Qwen3.7 Max 2026 06 08 vs Qwen: Qwen3.8 27B	`qwen/qwen3.7-max-2026-06-08`	1	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen3.7 Plus 2026 05 26	`moonshotai/kimi-k2.6`	27	`qwen/qwen3.7-plus-2026-05-26`	1
Google: Gemma 4 31B vs Reflection Beam 1.0	`google/gemma-4-31b-it`	26	`reflection/beam`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Beam	`deepseek/deepseek-v4-pro`	26	`reflection/beam-1.0`	2
MiniMax: MiniMax M3 vs XiaomiMiMo/MiMo-V2.6-Flash-RL	`minimax/minimax-m3`	25	`xiaomi/mimo-v2.6-flash-rl`	2
Xiaomi MiMo V2.6 Pro UltraSpeed vs Z.ai: GLM 5.3	`xiaomi/mimo-v2.6-pro-ultraspeed`	2	`z-ai/glm-5.3`	50
Xiaomi MiMo V2.5 vs Z.ai: GLM 5.2	`xiaomimimo/mimo-v2.5`	2	`z-ai/glm-5.2`	48
Xiaomi MiMo V2.5 Pro vs Z.ai: GLM 5.3 Flash	`xiaomimimo/mimo-v2.5-pro`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs GLM 5.2 Fast	`moonshotai/kimi-k3`	45	`z-ai/glm-5.2-fast`	2
DeepSeek: DeepSeek V4 Flash 0731 vs zai-org/glm-5.3-p	`deepseek/deepseek-v4-flash-0731`	35	`z-ai/glm-5.3-p`	2
DeepSeek: DeepSeek V4.1 Flash vs GLM-5.2	`deepseek/deepseek-v4.1-flash`	37	`zai-org/GLM-5.2`	2
OpenAI: GPT-4.1 vs OpenAI: gpt-oss-120b	`openai/gpt-4.1`	2	`openai/gpt-oss-120b`	38
OpenAI: GPT-4.1 Nano vs Qwen: Qwen3.8 27B	`openai/gpt-4.1-nano`	2	`qwen/qwen3.8-27b`	30
Anthropic: Claude Fable 5 vs MoonshotAI: Kimi K2.6	`anthropic/claude-fable-5`	2	`moonshotai/kimi-k2.6`	27
Anthropic: Claude Fable 5.1 vs Google: Gemma 4 31B	`anthropic/claude-fable-5.1`	2	`google/gemma-4-31b-it`	26
Anthropic: Claude Haiku 5.5 vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-haiku-5.5`	2	`deepseek/deepseek-v4-pro`	26
Anthropic: Claude Opus 4.6 vs MiniMax: MiniMax M3	`anthropic/claude-opus-4.6`	2	`minimax/minimax-m3`	25
Anthropic: Claude Opus 4.7 vs Z.ai: GLM 5.3	`anthropic/claude-opus-4.7`	2	`z-ai/glm-5.3`	50
Anthropic: Claude Opus 4.8 vs Z.ai: GLM 5.2	`anthropic/claude-opus-4.8`	2	`z-ai/glm-5.2`	48
Anthropic: Claude Opus 5 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-opus-5`	3	`z-ai/glm-5.3-flash`	48
Anthropic: Claude Opus 5.5 vs MoonshotAI: Kimi K3	`anthropic/claude-opus-5.5`	2	`moonshotai/kimi-k3`	45
Anthropic: Claude Sonnet 4.5 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-sonnet-4.5`	2	`deepseek/deepseek-v4-flash-0731`	35
Anthropic: Claude Sonnet 5 vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-sonnet-5`	2	`deepseek/deepseek-v4.1-flash`	37
Anthropic: Claude Sonnet 5.5 vs OpenAI: gpt-oss-120b	`anthropic/claude-sonnet-5.5`	2	`openai/gpt-oss-120b`	38
DeepSeek V4.1 Flash vs Qwen: Qwen3.8 27B	`deepseek/deepseek-v4-1-flash`	2	`qwen/qwen3.8-27b`	30
DeepSeek v4.1 Flash (1017) vs MoonshotAI: Kimi K2.6	`deepseek/deepseek-v4-1-flash-1017`	2	`moonshotai/kimi-k2.6`	27
google/gemini-3.1-pro vs Google: Gemma 4 31B	`google/gemini-3.1-pro`	2	`google/gemma-4-31b-it`	26
DeepSeek: DeepSeek V4 Pro 0423 vs Inception: Mercury 3	`deepseek/deepseek-v4-pro`	26	`inception/mercury-3`	1
MiniMax: MiniMax M3 vs MiniMax M3.1 Flash	`minimax/minimax-m3`	25	`minimax/minimax-m3-1-flash`	2
MiniMax-M3.1-Flash vs Z.ai: GLM 5.3	`minimax/minimax-m3.1-flash`	3	`z-ai/glm-5.3`	50
MiniMax M1 vs Z.ai: GLM 5.2	`minimaxai/minimax-m1-80k`	2	`z-ai/glm-5.2`	48
Kimi K3 Fast vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k3-fast-api`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs Qwen 3.6 Plus Uncensored	`moonshotai/kimi-k3`	45	`qwen/qwen-3-6-plus`	2
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen 3.7 Max	`deepseek/deepseek-v4-flash-0731`	35	`qwen/qwen-3-7-max`	2
DeepSeek: DeepSeek V4.1 Flash vs Qwen 3.7 Plus	`deepseek/deepseek-v4.1-flash`	37	`qwen/qwen-3-7-plus`	2
OpenAI: gpt-oss-120b vs Qwen 3.8 Flash	`openai/gpt-oss-120b`	38	`qwen/qwen-3-8-flash`	2
Qwen 3.8 Max vs Qwen: Qwen3.8 27B	`qwen/qwen-3-8-max`	2	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs fugu-ultra-v1.1	`moonshotai/kimi-k2.6`	27	`sakana-ai/fugu-ultra-v1.1`	1
Google: Gemma 4 31B vs ScaleDown Classify	`google/gemma-4-31b-it`	26	`scaledown/classify`	1
DeepSeek: DeepSeek V4 Pro 0423 vs ScaleDown Compress	`deepseek/deepseek-v4-pro`	26	`scaledown/compress`	1
MiniMax: MiniMax M3 vs ScaleDown Extract	`minimax/minimax-m3`	25	`scaledown/extract`	1
ScaleDown Summarize vs Z.ai: GLM 5.3	`scaledown/summarize`	1	`z-ai/glm-5.3`	50
Z.ai: GLM 5.2 vs Dolly 1 Security	`z-ai/glm-5.2`	48	`zro/dolly1-security`	1
MiniMax M3 Preview vs Z.ai: GLM 5.3 Flash	`minimax/minimax-m3-preview`	2	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs SpaceXAI: Grok 4.7	`moonshotai/kimi-k3`	45	`x-ai/grok-4.7`	2
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-5	`deepseek/deepseek-v4-flash-0731`	35	`openai/gpt-5`	2
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-5 Nano	`deepseek/deepseek-v4.1-flash`	37	`openai/gpt-5-nano`	2
OpenAI: GPT-5.1 vs OpenAI: gpt-oss-120b	`openai/gpt-5.1`	2	`openai/gpt-oss-120b`	38
OpenAI: GPT-5.2 vs Qwen: Qwen3.8 27B	`openai/gpt-5.2`	2	`qwen/qwen3.8-27b`	30
AionLabs: Aion 3.5 vs MoonshotAI: Kimi K2.6	`aion-labs/aion-3.5`	1	`moonshotai/kimi-k2.6`	27
AionLabs: Aion 3.5 Mini vs Google: Gemma 4 31B	`aion-labs/aion-3.5-mini`	1	`google/gemma-4-31b-it`	26
Trinity Large Thinking vs DeepSeek: DeepSeek V4 Pro 0423	`arcee-ai/trinity-large-thinking`	1	`deepseek/deepseek-v4-pro`	26
ByteDance Seed: Seed 2.1 Turbo vs MiniMax: MiniMax M3	`bytedance-seed/seed-2-1-turbo`	1	`minimax/minimax-m3`	25
dola-seed-2-1-turbo vs Z.ai: GLM 5.3	`bytedance/dola-seed-2-1-turbo-260628`	1	`z-ai/glm-5.3`	50
Doubao Seed 1.6 vs Z.ai: GLM 5.2	`bytedance/doubao-seed-1.6-251015`	1	`z-ai/glm-5.2`	48
Doubao Seed 1.6 Flash vs Z.ai: GLM 5.3 Flash	`bytedance/doubao-seed-1.6-flash-250828`	1	`z-ai/glm-5.3-flash`	48
Doubao Seed 1.8 vs MoonshotAI: Kimi K3	`bytedance/doubao-seed-1.8-251228`	1	`moonshotai/kimi-k3`	45
Doubao Seed 2.0 Code Preview vs DeepSeek: DeepSeek V4 Flash 0731	`bytedance/doubao-seed-2.0-code-preview-260215`	1	`deepseek/deepseek-v4-flash-0731`	35
Doubao Seed 2.0 Lite vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/doubao-seed-2.0-lite-260428`	1	`deepseek/deepseek-v4.1-flash`	37
Doubao Seed 2.0 Mini vs OpenAI: gpt-oss-120b	`bytedance/doubao-seed-2.0-mini-260428`	1	`openai/gpt-oss-120b`	38
Doubao Seed 2.0 Pro vs Qwen: Qwen3.8 27B	`bytedance/doubao-seed-2.0-pro-260215`	1	`qwen/qwen3.8-27b`	30
Doubao Seed 2.1 Pro vs MoonshotAI: Kimi K2.6	`bytedance/doubao-seed-2.1-pro-260628`	1	`moonshotai/kimi-k2.6`	27
Doubao Seed 2.1 Turbo vs Google: Gemma 4 31B	`bytedance/doubao-seed-2.1-turbo-260628`	1	`google/gemma-4-31b-it`	26
Doubao Seed Evolving vs DeepSeek: DeepSeek V4 Pro 0423	`bytedance/doubao-seed-evolving`	1	`deepseek/deepseek-v4-pro`	26
seed-2-0-code vs MiniMax: MiniMax M3	`bytedance/seed-2-0-code-preview-260328`	1	`minimax/minimax-m3`	25
seed-2-0-lite vs Z.ai: GLM 5.3	`bytedance/seed-2-0-lite-260428`	1	`z-ai/glm-5.3`	50
seed-2-0-mini vs Z.ai: GLM 5.2	`bytedance/seed-2-0-mini-260428`	1	`z-ai/glm-5.2`	48
seed-2-0-pro vs Z.ai: GLM 5.3 Flash	`bytedance/seed-2-0-pro-260328`	1	`z-ai/glm-5.3-flash`	48
google/gemma-4-31B-it-turbo vs MoonshotAI: Kimi K3	`google/gemma-4-31b-it-turbo`	2	`moonshotai/kimi-k3`	45
DeepSeek: DeepSeek V4 Flash 0731 vs inclusionAI: Ling 3.1 Flash	`deepseek/deepseek-v4-flash-0731`	35	`inclusionai/ling-3.1-flash`	2
DeepSeek: DeepSeek V4.1 Flash vs KAT Coder Air V2.5	`deepseek/deepseek-v4.1-flash`	37	`kwaipilot/kat-coder-air-v2.5`	1
KAT Coder Pro V2.5 vs OpenAI: gpt-oss-120b	`kwaipilot/kat-coder-pro-v2.5`	1	`openai/gpt-oss-120b`	38
Macaron V1 Tall vs Qwen: Qwen3.8 27B	`mindai/macaron-v1-tall`	2	`qwen/qwen3.8-27b`	30
Mistral: Ministral 3 14B 2512 vs MoonshotAI: Kimi K2.6	`mistralai/ministral-14b-2512`	2	`moonshotai/kimi-k2.6`	27
Google: Gemma 4 31B vs Mistral: Ministral 3 8B 2512	`google/gemma-4-31b-it`	26	`mistralai/ministral-8b-2512`	2
DeepSeek: DeepSeek V4 Pro 0423 vs Mistral: Mistral Medium 3.5	`deepseek/deepseek-v4-pro`	26	`mistralai/mistral-medium-3-5`	2
MiniMax: MiniMax M3 vs MoonshotAI: Kimi K2 0905	`minimax/minimax-m3`	25	`moonshotai/kimi-k2-0905`	2
moonshotai/Kimi-K2-Instruct-0905 vs Z.ai: GLM 5.3	`moonshotai/kimi-k2-instruct-0905`	2	`z-ai/glm-5.3`	50
morph-v3-fast vs Z.ai: GLM 5.3 Flash	`morph/morph-v3-fast`	1	`z-ai/glm-5.3-flash`	48
MoonshotAI: Kimi K3 vs morph-v3-large	`moonshotai/kimi-k3`	45	`morph/morph-v3-large`	1
DeepSeek: DeepSeek V4 Flash 0731 vs nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B	`deepseek/deepseek-v4-flash-0731`	35	`nvidia/nemotron-3-nano-omni-reasoning-30b-a3b`	2
DeepSeek: DeepSeek V4.1 Flash vs Nemotron 3 Super	`deepseek/deepseek-v4.1-flash`	37	`nvidia/nemotron-3-super`	1
OpenAI: gpt-oss-120b vs Ternary Bonsai 27B	`openai/gpt-oss-120b`	38	`prism-ml/ternary-bonsai-27b`	2
Qwen 3.8 2.4T vs Qwen: Qwen3.8 27B	`qwen/qwen-3-8-2-4t-a95b`	2	`qwen/qwen3.8-27b`	30
MoonshotAI: Kimi K2.6 vs Qwen VL OCR	`moonshotai/kimi-k2.6`	27	`qwen/qwen-vl-ocr`	1
Google: Gemma 4 31B vs Qwen VL OCR 2025 11 20	`google/gemma-4-31b-it`	26	`qwen/qwen-vl-ocr-2025-11-20`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen: Qwen3 235B A22B Instruct 2507	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-235b-a22b-2507`	1