COMPARE.

Unspecified

together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

Models^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/mistralai/Mistral-7B-Instruct-v0.1

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/mistralai/Mistral-Small-24B-Instruct-2501

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/openai/gpt-oss-20b

Models^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen2-72B-Instruct

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen2-VL-72B-Instruct

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo

Models^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

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

Models^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen2.5-VL-72B-Instruct

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-Coder-Next-FP8

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-VL-32B-Instruct

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3-VL-8B-Instruct

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/Qwen3.6-Plus

Models^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Qwen/QwQ-32B

Models^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/Salesforce/Llama-Rank-V1

Models^*

Maximum input

8,192 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/zai-org/GLM-4.5-Air-FP8

Models^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/zai-org/GLM-4.7

Models^*

Maximum input

202,752 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/zai-org/GLM-5

Models^*

Maximum input

202,752 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence