COMPARE.

Unspecified

dashscope/glm-5.1

Models^*

Maximum output

131,072 tokens^*

Maximum input

202,745 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

dashscope/glm-5.2

Models^*

Maximum output

131,072 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

databricks/databricks-gemini-3-7-flash

Models^*

Maximum output

65,536 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

databricks/databricks-gemini-3-8-flash

Models^*

Maximum output

65,536 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

databricks/databricks-llama-4-maverick

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

databricks/databricks-meta-llama-3-3-70b-instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/anthropic/claude-sonnet-4-6

Models^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/ByteDance/Seed-1.8

Models^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/ByteDance/Seed-2.0-code

Models^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/ByteDance/Seed-2.0-mini

Models^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/ByteDance/Seed-2.0-pro

Models^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/deepseek-ai/DeepSeek-V4-Flash

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/google/gemini-2.5-pro

Models^*

Maximum output

1,000,000 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/google/gemini-3.7-flash

Models^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/inclusionAI/Ling-3.0-flash

Models^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/meta-models/Muse-Glimmer-30B

Models^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/MiniMaxAI/MiniMax-M2.7

Models^*

Maximum input

196,608 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo

Models^*

Maximum input

196,608 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/MiniMaxAI/MiniMax-M3

Models^*

Maximum input

524,288 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/moonshotai/Kimi-K2.5

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/moonshotai/Kimi-K2.6

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/moonshotai/Kimi-K2.7-Code

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence