COMPARE.

Unspecified

oci/openai.gpt-5

Models^*

Maximum output

128,000 tokens^*

Maximum input

272,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/openai.gpt-5-mini

Models^*

Maximum output

128,000 tokens^*

Maximum input

272,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/openai.gpt-5-nano

Models^*

Maximum output

128,000 tokens^*

Maximum input

272,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/xai.grok-4.20-0309-non-reasoning

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

oci/xai.grok-4.20-non-reasoning

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

qwen_ai_platform/qwen3.7-plus

Models^*

Maximum output

65,536 tokens^*

Maximum input

991,808 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen.qwen3-coder-480b-a35b-v1:0

Models^*

Maximum output

16,384 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3-8B

Models

Context window

40,960 tokens

Maximum output

32,768 tokens

Total parameters

8.19 B

Open weights

Yes

Radar · unrated1/4 core tests · not enough evidenceqwen3-8b_none

Unspecified

qwencloud/qwen3.7-plus

Models^*

Maximum output

65,536 tokens^*

Maximum input

991,808 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/anthropic/claude-4-sonnet

Models^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/anthropic/claude-4.5-haiku

Models^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/anthropic/claude-4.5-sonnet

Models^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/openai/gpt-4o

Models^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

sambanova/Llama-4-Maverick-17B-128E-Instruct

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

scaleway/deepseek-v4-flash-0731

Models^*

Maximum output

32,768 tokens^*

Maximum input

256,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

scx-ai/DeepSeek-V4.1-flash

Models^*

Maximum output

375,000 tokens^*

Maximum input

1,000,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8

Models^*

Maximum output

262,144 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/deepseek-ai/DeepSeek-V3

Models^*

Maximum output

8,192 tokens^*

Maximum input

65,536 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/deepseek-ai/DeepSeek-V4-Pro-0813

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/Qwen/Qwen3.5-9B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/thinkingmachines/Inkling

Models^*

Maximum input

524,288 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

twelvelabs.marengo-embed-3-0-v1:0

Models^*

Maximum input

500 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

us.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

us.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