COMPARE.

microsoft

udop-large

Models

Open weights

Yes

Model license

mit

Checkpoint tensor payload

2.76 GiB

Architecture

udop

Radar · unrated0/4 core tests · not enough evidence

microsoft

udop-large-512

Models

Open weights

Yes

Model license

mit

Checkpoint tensor payload

2.76 GiB

Architecture

udop

Radar · unrated0/4 core tests · not enough evidence

microsoft

udop-large-512-300k

Models

Open weights

Yes

Model license

mit

Checkpoint tensor payload

2.76 GiB

Architecture

udop

Radar · unrated0/4 core tests · not enough evidence

zai

UI2Code_N

Models

Context window

65,536 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

19.17 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

UniRG-CXR

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

16.33 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

us.cohere.embed-v4:0

Models^*

Maximum input

128,000 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

us.twelvelabs.pegasus-1-5-v1:0

Models^*

Maximum output

98,304 tokens^*

Maximum input

261,120 tokens^*

API mode

Chat^*

Video input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

microsoft

UserLM-2.0

Models

Context window

131,072 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

29.92 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

UserRepGen-4B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

8.46 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

Veo 3.1

Models^*

Open weights

No^*

Model type

Video generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/deepseek/deepseek-r1

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/deepseek/deepseek-v3

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3-70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3-8b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3.1-70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-4-maverick

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/magistral-small

Models^*

Maximum output

64,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/mixtral-8x22b-instruct

Models^*

Maximum output

2,048 tokens^*

Maximum input

65,536 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-3-fast

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/meta/llama3-405b-instruct-maas

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/meta/llama3-70b-instruct-maas

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/meta/llama3-8b-instruct-maas

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/veo-3.0-generate-001

Models^*

Maximum input

1,024 tokens^*

API mode

Video generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/veo-3.1-generate-preview

Models^*

Maximum input

1,024 tokens^*

API mode

Video generation^*

Radar · unrated0/4 core tests · not enough evidence