COMPARE.

Unspecified

nebius/mistralai/Mistral-Nemo-Instruct-2407

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/NousResearch/Hermes-3-Llama-3.1-405B

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1

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

nebius/openbmb/MiniCPM-V-4_5

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen2-VL-7B-Instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen2.5-32B-Instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen2.5-72B-Instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen2.5-Coder-7B

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen3-14B

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen3-235B-A22B

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

nebius/Qwen/Qwen3-235B-A22B-Instruct-2507

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

nebius/Qwen/Qwen3-30B-A3B

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen3-30B-A3B-Instruct-2507

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

nebius/Qwen/Qwen3-32B

Models^*

Maximum output

40,960 tokens^*

Maximum input

40,960 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen3-4B

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/reflection/beam

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/zai-org/GLM-5.3

Models^*

Maximum input

1,024,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-H-4B-Base-8K

Models

Context window

8,192 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

8.36 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-H-56B-Base-8K

Models

Context window

8,192 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

104.91 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-H-8B-Base-8K

Models

Context window

8,192 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

15.09 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-H-8B-Reasoning-128K

Models

Context window

131,072 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

15.09 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-Labs-Diffusion-14B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

25.16 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-Labs-Diffusion-3B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

7.14 GiB

Radar · unrated0/4 core tests · not enough evidence

nvidia

Nemotron-Labs-Diffusion-8B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

15.81 GiB

Radar · unrated0/4 core tests · not enough evidence