COMPARE.

Unspecified

vertex_ai/deepseek-ai/deepseek-v3.2-maas

Models^*

Maximum output

32,768 tokens^*

Maximum input

163,840 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/xai/grok-4.20-non-reasoning

Models^*

Maximum output

2,000,000 tokens^*

Maximum input

2,000,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/xai/grok-4.3

Models^*

Maximum output

200,000 tokens^*

Maximum input

200,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/xai/grok-4.6

Models^*

Maximum output

524,288 tokens^*

Maximum input

524,288 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/xai/grok-4.7

Models^*

Maximum output

524,288 tokens^*

Maximum input

524,288 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

amazon

amazon.nova-lite-v1:0

Models^*

Maximum output

10,000 tokens^*

Maximum input

300,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anthropic.claude-3-5-haiku-20241022-v1:0

Models^*

Maximum output

8,192 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

apac.amazon.nova-2-lite-v1:0

Models^*

Maximum output

64,000 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/FW-Kimi-K2.5

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/FW-Kimi-K3

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

azure_ai/grok-4-20-reasoning

Models^*

Maximum output

8,192 tokens^*

Maximum input

262,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/kimi-k2-thinking

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/kimi-k2.6

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/kimi-k2.7-code

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/gpt-4o-mini

Models^*

Maximum output

16,384 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/gpt-4o-mini-2024-07-18

Models^*

Maximum output

16,384 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/gpt-5.1-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

111,616 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/o1

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/o1-2024-12-17

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/global-standard/gpt-4o-2024-11-20

Models^*

Maximum output

16,384 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/gpt-5.1-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

111,616 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/us/gpt-4o-mini

Models^*

Maximum output

16,384 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/us/gpt-4o-mini-2024-07-18

Models^*

Maximum output

16,384 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/us/gpt-5.1-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

111,616 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence