COMPARE.

Unspecified

vercel_ai_gateway/alibaba/qwen3-coder

Models^*

Maximum output

66,536 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/amazon/nova-micro

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/cohere/command-r

Models^*

Maximum output

4,096 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/cohere/command-r-plus

Models^*

Maximum output

4,096 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3.1-8b

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3.2-3b

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3.3-70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/codestral

Models^*

Maximum output

4,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/ministral-3b

Models^*

Maximum output

4,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/mistral-large

Models^*

Maximum output

4,000 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/moonshotai/kimi-k2

Models^*

Maximum output

16,384 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-3.5-turbo

Models^*

Maximum output

4,096 tokens^*

Maximum input

16,385 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-2

Models^*

Maximum output

4,000 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-3

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-3-mini

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-3-mini-fast

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/xai/grok-4

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/zai/glm-4.5

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/zai/glm-4.5-air

Models^*

Maximum output

96,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/codestral-2

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/codestral-2@001

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/codestral-2501

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/codestral@2405

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/codestral@latest

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence