COMPARE.

Unspecified

us.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

us.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

vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022

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

vertex_ai/deepseek-ai/deepseek-r1-0528-maas

Models^*

Maximum output

8,192 tokens^*

Maximum input

65,336 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas

Models^*

Maximum output

1,048,576 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemini-3.1-flash-image-preview

Models^*

Maximum output

32,768 tokens^*

Maximum input

65,536 tokens^*

Reasoning

No^*

API mode

Image generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemini-embedding-2

Models^*

Maximum input

8,192 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemini-embedding-2-preview

Models^*

Maximum input

8,192 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

volcengine/doubao-seed-2-1-lite-260915

Models^*

Maximum output

256,000 tokens^*

Maximum input

1,024,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-3-8b-instruct

Models^*

Maximum output

1,024 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/mistralai/mistral-large

Models^*

Maximum output

16,384 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/claude-haiku-4-5

Models^*

Maximum output

64,000 tokens^*

Maximum input

200,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/gemini-3.5-flash-lite

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

aihubmix/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

aihubmix/qwen3.7-plus

Models^*

Maximum output

131,072 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/qwen3.8-flash

Models^*

Maximum output

131,072 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/qwen3.8-max

Models^*

Maximum output

131,072 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/FW-GPT-OSS-120B

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/FW-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/FW-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_ai/FW-MiniMax-M3

Models^*

Maximum output

512,000 tokens^*

Maximum input

512,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/grok-4-20-non-reasoning

Models^*

Maximum output

8,192 tokens^*

Maximum input

262,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/MAI-Thinking-1

Models^*

Maximum output

64,000 tokens^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure/eu/gpt-5.2-chat

Models^*

Maximum output

16,384 tokens^*

Maximum input

111,616 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence