COMPARE.

Unspecified

hyperbolic/deepseek-ai/DeepSeek-R1-0528

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

hyperbolic/deepseek-ai/DeepSeek-V3

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

hyperbolic/deepseek-ai/DeepSeek-V3-0324

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

hyperbolic/meta-llama/Llama-3.2-3B-Instruct

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

hyperbolic/meta-llama/Llama-3.3-70B-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

hyperbolic/meta-llama/Meta-Llama-3-70B-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

hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct

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

hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct

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

hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct

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

hyperbolic/moonshotai/Kimi-K2-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

hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B

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

hyperbolic/Qwen/Qwen2.5-72B-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

hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct

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

hyperbolic/Qwen/Qwen3-235B-A22B

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

hyperbolic/Qwen/QwQ-32B

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/deepseek-v3-0324

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/hermes3-405b

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/hermes3-70b

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/hermes3-8b

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/lfm-40b

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/lfm-7b

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/llama-4-maverick-17b-128e-instruct-fp8

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lambda_ai/llama-4-scout-17b-16e-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

16,384 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lambda_ai/llama3.1-405b-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