COMPARE.

Unspecified

vercel_ai_gateway/anthropic/claude-3-haiku

Models^*

Maximum output

4,096 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-opus

Models^*

Maximum output

4,096 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-haiku

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-4-opus

Models^*

Maximum output

32,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-4.1

Models^*

Maximum output

32,768 tokens^*

Maximum input

1,047,576 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-4.1-mini

Models^*

Maximum output

32,768 tokens^*

Maximum input

1,047,576 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-4.1-nano

Models^*

Maximum output

32,768 tokens^*

Maximum input

1,047,576 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-4o

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

vercel_ai_gateway/openai/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

vercel_ai_gateway/openai/o1

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/o3

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/o4-mini

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/claude-3-5-sonnet@20240620

Models^*

Maximum output

8,192 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas

Models^*

Maximum output

1,000,000 tokens^*

Maximum input

1,000,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas

Models^*

Maximum output

10,000,000 tokens^*

Maximum input

10,000,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas

Models^*

Maximum output

16,384 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/zai-org/glm-4.7-maas

Models^*

Maximum output

128,000 tokens^*

Maximum input

200,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

volcengine/doubao-seed-2-1-pro-260628

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

volcengine/doubao-seed-2-1-pro-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

volcengine/doubao-seed-2-1-turbo-260628

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B

Models^*

Maximum input

1,049,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/coding-glm-5.3

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

aihubmix/coding-xiaomi-mimo-v2.5-pro

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

aihubmix/deepseek-v4-flash

Models^*

Maximum output

384,000 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence