COMPARE.

Unspecified

perplexity/pplx-7b-chat

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-embed-context-v1-0.6b

Models^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-embed-context-v1-4b

Models^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-embed-v1-0.6b

Models^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-embed-v1-4b

Models^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/sonar-medium-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/sonar-small-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/openai/o1

Models^*

Reasoning

Yes^*

API mode

Chat^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/openai/o1-mini

Models^*

Reasoning

Yes^*

API mode

Chat^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/openai/o4-mini

Models^*

Reasoning

Yes^*

API mode

Chat^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

runwayml/gen4_image

Models^*

API mode

Image generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

runwayml/gen4_image_turbo

Models^*

API mode

Image generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

runwayml/hailuo3

Models^*

API mode

Video generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-13b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-13b-f

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-70b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-70b-b-f

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-7b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sagemaker/meta-textgeneration-llama-2-7b-f

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sambanova/DeepSeek-R1

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

scaledown/classify

Models^*

Tool calling

No^*

API mode

Chat^*

Image input

No^*

System messages

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

scaledown/compress

Models^*

Tool calling

No^*

API mode

Chat^*

Image input

No^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

scaledown/decisions

Models^*

Tool calling

No^*

API mode

Chat^*

Image input

No^*

System messages

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

scaledown/summarize

Models^*

Tool calling

No^*

API mode

Chat^*

Image input

No^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence