COMPARE.

Unspecified

novita/deepseek/deepseek-r1-distill-llama-70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Reasoning

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-r1-distill-qwen-14b

Models^*

Maximum output

16,384 tokens^*

Maximum input

32,768 tokens^*

Reasoning

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-r1-distill-qwen-32b

Models^*

Maximum output

32,000 tokens^*

Maximum input

64,000 tokens^*

Reasoning

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-r1/community

Models^*

Maximum output

8,000 tokens^*

Maximum input

64,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-v3-turbo

Models^*

Maximum output

16,000 tokens^*

Maximum input

64,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/google/gemma-3-12b-it

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-3.2-3b-instruct

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-30b-a3b-fp8

Models^*

Maximum output

20,000 tokens^*

Maximum input

40,960 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-4b-fp8

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-coder-next

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/sao10k/l3-70b-euryale-v2.1

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/Sao10K/L3-8B-Stheno-v3.2

Models^*

Maximum output

32,000 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/sao10k/l31-70b-euryale-v2.2

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/skywork/r1v4-lite

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/thudm/glm-4-32b-0414

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.command-a-vision

Models^*

Maximum output

8,192 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/meta.llama-3.2-90b-vision-instruct

Models^*

Maximum output

4,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/meta.llama-4-maverick-17b-128e-instruct-fp8

Models^*

Maximum output

8,192 tokens^*

Maximum input

1,048,576 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/DeepSeek-R1-Distill-Llama-70B

Models^*

Maximum output

131,000 tokens^*

Maximum input

131,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/gpt-oss-120b

Models^*

Maximum output

131,000 tokens^*

Maximum input

131,000 tokens^*

Reasoning

Yes^*

Tool calling

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/gpt-oss-20b

Models^*

Maximum output

131,000 tokens^*

Maximum input

131,000 tokens^*

Reasoning

Yes^*

Tool calling

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/llava-v1.6-mistral-7b-hf

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

Tool calling

No^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/Mistral-Small-3.2-24B-Instruct-2506

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ovhcloud/Qwen2.5-VL-72B-Instruct

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

Tool calling

No^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence