COMPARE.

Unspecified

lambda_ai/llama3.1-70b-instruct-fp8

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

lambda_ai/llama3.1-8b-instruct

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

lambda_ai/llama3.1-nemotron-70b-instruct-fp8

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

lambda_ai/llama3.2-3b-instruct

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

lambda_ai/llama3.3-70b-instruct-fp8

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

lambda_ai/qwen25-coder-32b-instruct

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

libertai/deepseek-v4-flash

Models^*

Maximum output

200,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

libertai/gemma-4-31b-it

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

libertai/hermes-3-8b-tee

Models^*

Maximum output

16,000 tokens^*

Maximum input

16,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

libertai/qwen3.5-122b-a10b

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

libertai/qwen3.6-27b

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

libertai/qwen3.6-35b-a3b

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

meta.llama3-2-11b-instruct-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

meta.llama3-2-90b-instruct-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

minimax/MiniMax-H3-Max

Models^*

API mode

Video generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/labs-leanstral-1-5

Models^*

Maximum output

131,072 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/mistral-tiny

Models^*

Maximum output

8,191 tokens^*

Maximum input

32,000 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/open-mistral-nemo

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

moonshot/moonshot-v1-128k-vision-preview

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

moonshot/moonshot-v1-32k-vision-preview

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

moonshot/moonshot-v1-8k-vision-preview

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/baidu/ernie-4.5-21B-a3b

Models^*

Maximum output

8,000 tokens^*

Maximum input

120,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-ocr

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-r1

Models^*

Maximum output

16,000 tokens^*

Maximum input

64,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence