COMPARE.

Unspecified

scaleway/qwen/qwen3.6-35b-a3b

Models^*

Maximum output

16,384 tokens^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

snowflake/mistral-large2

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

snowflake/openai-gpt-5-mini

Models^*

Maximum output

16,384 tokens^*

Maximum input

1,000,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

snowflake/openai-gpt-5-nano

Models^*

Maximum output

16,384 tokens^*

Maximum input

5,000,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/meta-models/Muse-Spark-Open-816B-A42B

Models^*

Maximum input

1,048,576 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/reflection/Beam-1.0-501B-A23B

Models^*

Maximum input

1,048,576 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

us.meta.llama3-1-405b-instruct-v1:0

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

us.meta.llama3-2-1b-instruct-v1:0

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

us.meta.llama3-2-3b-instruct-v1:0

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

us.writer.palmyra-x4-v1:0

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

us.writer.palmyra-x5-v1:0

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/amazon/nova-lite

Models^*

Maximum output

8,192 tokens^*

Maximum input

300,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/amazon/nova-pro

Models^*

Maximum output

8,192 tokens^*

Maximum input

300,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/cohere/command-a

Models^*

Maximum output

8,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/google/gemma-2-9b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/meta/llama-3.2-11b

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/meta/llama-3.2-90b

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/meta/llama-4-scout

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/devstral-small

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/magistral-medium

Models^*

Maximum output

64,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/mistral/ministral-8b

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-small

Models^*

Maximum output

4,000 tokens^*

Maximum input

32,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vercel_ai_gateway/openai/gpt-4-turbo

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