COMPARE.

Unspecified

meta.llama4-scout-17b-instruct-v1:0

Models^*

Maximum output

8,192 tokens^*

Maximum input

10,000,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/magistral-medium-latest

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/magistral-small-latest

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

moonshot/kimi-k2.5

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

moonshot/kimi-k2.6

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

multimodalembedding

Models^*

Maximum input

2,048 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/baidu/ernie-4.5-vl-28b-a3b-thinking

Models^*

Maximum output

65,536 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v3-0324

Models^*

Maximum output

65,536 tokens^*

Maximum input

163,840 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v4-flash

Models^*

Maximum output

393,216 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v4-flash-0731

Models^*

Maximum output

393,216 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v4-flash-vision-exp

Models^*

Maximum output

393,216 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v4-pro

Models^*

Maximum output

393,216 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v4-pro-0813

Models^*

Maximum output

393,216 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/kwaipilot/kat-coder-pro

Models^*

Maximum output

128,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m2.1

Models^*

Maximum output

131,072 tokens^*

Maximum input

204,800 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m2.5

Models^*

Maximum output

131,100 tokens^*

Maximum input

204,800 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m2.5-highspeed

Models^*

Maximum output

131,100 tokens^*

Maximum input

204,800 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m2.7

Models^*

Maximum output

131,072 tokens^*

Maximum input

204,800 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m2.7-highspeed

Models^*

Maximum output

131,072 tokens^*

Maximum input

204,800 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/minimax/minimax-m3

Models^*

Maximum output

131,072 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k2.5

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k2.6

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k2.7-code

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k3

Models^*

Maximum output

1,048,576 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence