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: DeepSeek V4 Flash 0423 vs @cf/meta/llama-3.2-11b-vision-instruct	`deepseek/deepseek-v4-flash`	25	`meta-llama/llama-3.2-11b-vision-instruct`	2
DeepSeek: DeepSeek V4 Pro 0423 vs mistralai/Mistral-Small-3.2-24B-Instruct-2506	`deepseek/deepseek-v4-pro`	26	`mistralai/mistral-small-3.2-24b-instruct-2506`	3
Google: Gemma 4 31B vs OpenAI: GPT-4 Turbo	`google/gemma-4-31b-it`	25	`openai/gpt-4-turbo`	4
DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-4o	`deepseek/deepseek-v4.1-flash`	23	`openai/gpt-4o`	4
MoonshotAI: Kimi K2.7 Code vs Qwen: Qwen3 30B A3B	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3-30b-a3b`	3
granite-4.1-8b vs Z.ai: GLM 5.2	`ibm-granite/granite-4.1-8b`	2	`z-ai/glm-5.2`	44
@cf/qwen/qwen2.5-coder-32b-instruct vs Z.ai: GLM 5.3	`qwen/qwen2.5-coder-32b-instruct`	2	`z-ai/glm-5.3`	43
Qwen3-VL-8B-Thinking vs Z.ai: GLM 5.3 Flash	`qwen/qwen3-vl-8b-thinking`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-3.5 Turbo	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-3.5-turbo`	4
MoonshotAI: Kimi K3 vs Qwen MT Plus	`moonshotai/kimi-k3`	39	`qwen/qwen-mt-plus`	3
OpenAI: GPT-4 vs OpenAI: gpt-oss-120b	`openai/gpt-4`	4	`openai/gpt-oss-120b`	36
MiniMax Hailuo 3 (H3) vs MoonshotAI: Kimi K2.6	`minimax/hailuo-3`	2	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs remm-slerp:l2-13b	`deepseek/deepseek-v4-flash`	25	`undi95/remm-slerp-l2-13b`	2
Alibaba Wan 2.7 vs DeepSeek: DeepSeek V4 Pro 0423	`alibaba/wan-2.7`	2	`deepseek/deepseek-v4-pro`	26
Google: Gemma 4 31B vs Lightricks LTX 2.3	`google/gemma-4-31b-it`	25	`lightricks/ltx-2.3`	2
DeepSeek: DeepSeek V4.1 Flash vs Lightricks LTX 2.3 Fast	`deepseek/deepseek-v4.1-flash`	23	`lightricks/ltx-2.3-fast`	2
Kling Video 3.0 Omni Pro vs MoonshotAI: Kimi K2.7 Code	`kling/o3-pro`	2	`moonshotai/kimi-k2.7-code`	19
Kling Video 3.0 Pro vs Z.ai: GLM 5.2	`kling/v3-pro`	2	`z-ai/glm-5.2`	44
Google Veo 3.1 vs Z.ai: GLM 5.3	`google/veo-3.1`	2	`z-ai/glm-5.3`	43
Google Veo 3.1 Fast vs Z.ai: GLM 5.3 Flash	`google/veo-3.1-fast`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI Sora 2	`deepseek/deepseek-v4-flash-0731`	33	`openai/sora-2`	2
MoonshotAI: Kimi K3 vs OpenAI Sora 2 Pro	`moonshotai/kimi-k3`	39	`openai/sora-2-pro`	2
OpenAI: gpt-oss-120b vs Runway Gen-4.5	`openai/gpt-oss-120b`	36	`runway/gen-4.5`	2
MoonshotAI: Kimi K2.6 vs grok-4.20-0309-reasoning	`moonshotai/kimi-k2.6`	33	`x-ai/grok-4.20-reasoning`	3
DeepSeek: DeepSeek V4 Flash 0423 vs SpaceXAI: Grok 4.20	`deepseek/deepseek-v4-flash`	25	`x-ai/grok-4.20`	2
DeepSeek: DeepSeek V4 Pro 0423 vs GPT 5.4	`deepseek/deepseek-v4-pro`	26	`openai/gpt-5.4-2026-03-05`	2
Google: Gemma 4 31B vs GPT 5.5	`google/gemma-4-31b-it`	25	`openai/gpt-5.5-2026-04-23`	2
DeepSeek: DeepSeek V4.1 Flash vs GPT 5.6 Luna	`deepseek/deepseek-v4.1-flash`	23	`openai/gpt-5.6-luna-az`	1
MoonshotAI: Kimi K2.7 Code vs GPT 5.6 Sol	`moonshotai/kimi-k2.7-code`	19	`openai/gpt-5.6-sol-az`	1
GPT 5.6 Terra vs Z.ai: GLM 5.2	`openai/gpt-5.6-terra-az`	1	`z-ai/glm-5.2`	44
LongCat 2.0 vs Z.ai: GLM 5.3	`meituan-longcat/longcat-2.0`	1	`z-ai/glm-5.3`	43
DeepSeek V4 Pro vs Z.ai: GLM 5.3 Flash	`deepseek-ai/DeepSeek-V4-Pro`	2	`z-ai/glm-5.3-flash`	41
DeepSeek V4.1 Flash (rolling) vs DeepSeek: DeepSeek V4 Flash 0731	`deepseek/deepseek-flash`	2	`deepseek/deepseek-v4-flash-0731`	33
Deepseek V4P1 Flash on Fireworks vs MoonshotAI: Kimi K3	`deepseek/deepseek-v4p1-flash`	2	`moonshotai/kimi-k3`	39
Gemini 2.5 Flash Lite vs OpenAI: gpt-oss-120b	`google/gemini-2.5-flash-lite-preview-06-17`	2	`openai/gpt-oss-120b`	36
Google: Gemini 3.1 Flash Lite Preview vs MoonshotAI: Kimi K2.6	`google/gemini-3.1-flash-lite-preview`	3	`moonshotai/kimi-k2.6`	33
DeepSeek: DeepSeek V4 Flash 0423 vs Google Gemini Omni Flash	`deepseek/deepseek-v4-flash`	25	`google/gemini-omni-flash`	1
DeepSeek: DeepSeek V4 Pro 0423 vs deepseek-v4-pro	`deepseek/deepseek-v4-pro`	26	`lightning-ai/deepseek-v4-pro`	2
Google: Gemma 4 31B vs Macaron V1 Venti	`google/gemma-4-31b-it`	25	`mindai/macaron-v1-venti`	2
DeepSeek: DeepSeek V4.1 Flash vs MiniMax-M3	`deepseek/deepseek-v4.1-flash`	23	`MiniMaxAI/MiniMax-M3`	2
MoonshotAI: Kimi K2.7 Code vs Kimi K3 Fast on Fireworks	`moonshotai/kimi-k2.7-code`	19	`moonshotai/kimi-k3-fast`	2
Qwen Flash vs Z.ai: GLM 5.2	`qwen/qwen-flash`	1	`z-ai/glm-5.2`	44
Qwen Flash 2025 07 28 vs Z.ai: GLM 5.3	`qwen/qwen-flash-2025-07-28`	1	`z-ai/glm-5.3`	43
Qwen Plus vs Z.ai: GLM 5.3 Flash	`qwen/qwen-plus`	1	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen Plus 2025 07 28	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen-plus-2025-07-28`	1
MoonshotAI: Kimi K3 vs Qwen Plus 2025 09 11	`moonshotai/kimi-k3`	39	`qwen/qwen-plus-2025-09-11`	1
OpenAI: gpt-oss-120b vs Qwen Plus 2025 12 01	`openai/gpt-oss-120b`	36	`qwen/qwen-plus-2025-12-01`	1
MoonshotAI: Kimi K2.6 vs Qwen3 Coder Flash	`moonshotai/kimi-k2.6`	33	`qwen/qwen3-coder-flash`	1
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3 Coder Flash 2025 07 28	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3-coder-flash-2025-07-28`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Qwen3 Coder Plus	`deepseek/deepseek-v4-pro`	26	`qwen/qwen3-coder-plus`	1
Google: Gemma 4 31B vs Qwen3 Coder Plus 2025 07 22	`google/gemma-4-31b-it`	25	`qwen/qwen3-coder-plus-2025-07-22`	1
DeepSeek: DeepSeek V4.1 Flash vs Qwen3 Coder Plus 2025 09 23	`deepseek/deepseek-v4.1-flash`	23	`qwen/qwen3-coder-plus-2025-09-23`	1
MoonshotAI: Kimi K2.7 Code vs Qwen3.5 Flash 2026 02 23	`moonshotai/kimi-k2.7-code`	19	`qwen/qwen3.5-flash-2026-02-23`	1
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`	44
Qwen3.6 Flash vs Z.ai: GLM 5.3	`qwen/qwen3.6-flash`	1	`z-ai/glm-5.3`	43
Qwen3.6 Flash 2026 04 16 vs Z.ai: GLM 5.3 Flash	`qwen/qwen3.6-flash-2026-04-16`	1	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen3.7 Flash	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen3.7-flash`	1
MoonshotAI: Kimi K3 vs Qwen3.7 Flash 2026 07 15	`moonshotai/kimi-k3`	39	`qwen/qwen3.7-flash-2026-07-15`	1
OpenAI: gpt-oss-120b vs Qwen3.7 Max 2026 05 20	`openai/gpt-oss-120b`	36	`qwen/qwen3.7-max-2026-05-20`	1
MoonshotAI: Kimi K2.6 vs Qwen3.7 Max 2026 06 08	`moonshotai/kimi-k2.6`	33	`qwen/qwen3.7-max-2026-06-08`	1
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen3.7 Plus 2026 05 26	`deepseek/deepseek-v4-flash`	25	`qwen/qwen3.7-plus-2026-05-26`	1
DeepSeek: DeepSeek V4 Pro 0423 vs Inkling	`deepseek/deepseek-v4-pro`	26	`thinkingmachines/inkling-1m`	2
Google: Gemma 4 31B vs Xiaomi MiMo V2.5	`google/gemma-4-31b-it`	25	`xiaomimimo/mimo-v2.5`	2
DeepSeek: DeepSeek V4.1 Flash vs Xiaomi MiMo V2.5 Pro	`deepseek/deepseek-v4.1-flash`	23	`xiaomimimo/mimo-v2.5-pro`	2
MoonshotAI: Kimi K2.7 Code vs zai-org/glm-5.3-p	`moonshotai/kimi-k2.7-code`	19	`z-ai/glm-5.3-p`	2
Z.ai: GLM 5.2 vs GLM-5.2	`z-ai/glm-5.2`	44	`zai-org/GLM-5.2`	2
OpenAI: GPT-4.1 Nano vs Z.ai: GLM 5.3	`openai/gpt-4.1-nano`	2	`z-ai/glm-5.3`	43
Anthropic: Claude Fable 5 vs Z.ai: GLM 5.3 Flash	`anthropic/claude-fable-5`	3	`z-ai/glm-5.3-flash`	41
Anthropic: Claude Fable 5.1 vs DeepSeek: DeepSeek V4 Flash 0731	`anthropic/claude-fable-5.1`	2	`deepseek/deepseek-v4-flash-0731`	33
Anthropic: Claude Opus 4.6 vs MoonshotAI: Kimi K3	`anthropic/claude-opus-4.6`	3	`moonshotai/kimi-k3`	39
Anthropic: Claude Opus 4.7 vs OpenAI: gpt-oss-120b	`anthropic/claude-opus-4.7`	3	`openai/gpt-oss-120b`	36
Anthropic: Claude Opus 4.8 vs MoonshotAI: Kimi K2.6	`anthropic/claude-opus-4.8`	3	`moonshotai/kimi-k2.6`	33
Anthropic: Claude Opus 5 vs DeepSeek: DeepSeek V4 Flash 0423	`anthropic/claude-opus-5`	5	`deepseek/deepseek-v4-flash`	25
Anthropic: Claude Sonnet 4.5 vs DeepSeek: DeepSeek V4 Pro 0423	`anthropic/claude-sonnet-4.5`	2	`deepseek/deepseek-v4-pro`	26
Anthropic: Claude Sonnet 4.6 vs Google: Gemma 4 31B	`anthropic/claude-sonnet-4.6`	3	`google/gemma-4-31b-it`	25
Anthropic: Claude Sonnet 5 vs DeepSeek: DeepSeek V4.1 Flash	`anthropic/claude-sonnet-5`	3	`deepseek/deepseek-v4.1-flash`	23
DeepSeek V4.1 Flash vs MoonshotAI: Kimi K2.7 Code	`deepseek/deepseek-v4-1-flash`	2	`moonshotai/kimi-k2.7-code`	19
google/gemini-3.1-pro vs Z.ai: GLM 5.2	`google/gemini-3.1-pro`	2	`z-ai/glm-5.2`	44
MiniMax M1 vs Z.ai: GLM 5.3	`minimaxai/minimax-m1-80k`	2	`z-ai/glm-5.3`	43
Kimi K3 Fast vs Z.ai: GLM 5.3 Flash	`moonshotai/kimi-k3-fast-api`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs Qwen 3.6 Plus Uncensored	`deepseek/deepseek-v4-flash-0731`	33	`qwen/qwen-3-6-plus`	2
MoonshotAI: Kimi K3 vs Qwen 3.7 Max	`moonshotai/kimi-k3`	39	`qwen/qwen-3-7-max`	2
OpenAI: gpt-oss-120b vs Qwen 3.7 Plus	`openai/gpt-oss-120b`	36	`qwen/qwen-3-7-plus`	2
MoonshotAI: Kimi K2.6 vs Qwen 3.8 Flash	`moonshotai/kimi-k2.6`	33	`qwen/qwen-3-8-flash`	2
DeepSeek: DeepSeek V4 Flash 0423 vs Qwen 3.8 Max	`deepseek/deepseek-v4-flash`	25	`qwen/qwen-3-8-max`	2
DeepSeek: DeepSeek V4 Pro 0423 vs fugu-ultra-v1.1	`deepseek/deepseek-v4-pro`	26	`sakana-ai/fugu-ultra-v1.1`	1
Google: Gemma 4 31B vs ScaleDown Classify	`google/gemma-4-31b-it`	25	`scaledown/classify`	1
DeepSeek: DeepSeek V4.1 Flash vs ScaleDown Compress	`deepseek/deepseek-v4.1-flash`	23	`scaledown/compress`	1
MoonshotAI: Kimi K2.7 Code vs ScaleDown Extract	`moonshotai/kimi-k2.7-code`	19	`scaledown/extract`	1
ScaleDown Summarize vs Z.ai: GLM 5.2	`scaledown/summarize`	1	`z-ai/glm-5.2`	44
MiniMax M3 Preview vs Z.ai: GLM 5.3	`minimax/minimax-m3-preview`	2	`z-ai/glm-5.3`	43
OpenAI: GPT-5 vs Z.ai: GLM 5.3 Flash	`openai/gpt-5`	2	`z-ai/glm-5.3-flash`	41
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-5.1	`deepseek/deepseek-v4-flash-0731`	33	`openai/gpt-5.1`	2
MoonshotAI: Kimi K3 vs OpenAI: GPT-5.2	`moonshotai/kimi-k3`	39	`openai/gpt-5.2`	2
GPT 5.2 vs OpenAI: gpt-oss-120b	`openai/gpt-5.2-2025-12-11`	2	`openai/gpt-oss-120b`	36
MoonshotAI: Kimi K2.6 vs GPT 5.4 mini	`moonshotai/kimi-k2.6`	33	`openai/gpt-5.4-mini-2026-03-17`	2
DeepSeek: DeepSeek V4 Flash 0423 vs GPT 5.4 nano	`deepseek/deepseek-v4-flash`	25	`openai/gpt-5.4-nano-2026-03-17`	2
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 Google: Gemma 4 31B	`bytedance-seed/seed-2-1-turbo`	1	`google/gemma-4-31b-it`	25
Doubao Seed 1.6 vs DeepSeek: DeepSeek V4.1 Flash	`bytedance/doubao-seed-1.6-251015`	1	`deepseek/deepseek-v4.1-flash`	23