COMPARE.

Unspecified

mistral/mistral-small

Models^*

Maximum output

8,191 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-small-2507

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

mistral/voxtral-small-latest

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

novita/google/gemma-4-26b-a4b-it

Models^*

Maximum output

131,072 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/google/gemma-4-31b-it

Models^*

Maximum output

131,072 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-3.3-70b-instruct

Models^*

Maximum output

12,288 tokens^*

Maximum input

12,288 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k2-0905

Models^*

Maximum output

100,352 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/moonshotai/kimi-k2-instruct

Models^*

Maximum output

100,352 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/nvidia/nemotron-3-nano-30b-a3b

Models^*

Maximum output

32,768 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/openai/gpt-oss-20b

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen-2.5-72b-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen2.5-7b-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-235b-a22b-instruct-2507

Models^*

Maximum output

16,384 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-235b-a22b-thinking-2507

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-coder-30b-a3b-instruct

Models^*

Maximum output

32,768 tokens^*

Maximum input

160,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-coder-480b-a35b-instruct

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-max

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-vl-235b-a22b-thinking

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.5-122b-a10b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.5-27b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.5-35b-a3b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.5-397b-a17b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.6-27b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3.6-35b-a3b

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence