COMPARE.

Unspecified

inferenceapis/qwen3-vl

Models^*

Maximum input

262,144 tokens^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

inferenceapis/qwen3-vl-235b

Models^*

Maximum input

262,144 tokens^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

kimi-k2-thinking-251104

Models^*

Maximum output

32,768 tokens^*

Maximum input

229,376 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lambda_ai/deepseek-llama3.3-70b

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

lambda_ai/deepseek-r1-0528

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

lambda_ai/deepseek-r1-671b

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

lambda_ai/llama3.2-11b-vision-instruct

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

lambda_ai/qwen3-32b-fp8

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

libertai/deepseek-v4-flash-thinking

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

libertai/gemma-4-31b-it-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

libertai/qwen3.5-122b-a10b-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

libertai/qwen3.6-27b-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

libertai/qwen3.6-35b-a3b-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

meta.llama3-1-70b-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

meta.llama3-1-8b-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

meta.llama3-3-70b-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

mistral/codestral-2508

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

mistral/codestral-latest

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

mistral/devstral-latest

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/devstral-medium-latest

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/devstral-small-latest

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/mistral-code-agent-latest

Models^*

Maximum output

256,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/mistral-code-fim-latest

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

mistral/mistral-code-latest

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