COMPARE.

Unspecified

gpt-4o-transcribe

Models^*

Maximum output

2,000 tokens^*

Maximum input

16,000 tokens^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gpt-4o-transcribe-diarize

Models^*

Maximum output

2,000 tokens^*

Maximum input

16,000 tokens^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gpt-image-2-2026-04-21

Models^*

API mode

Image generation^*

Image input

Yes^*

PDF input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gpt-image-2.5-flare-2026-09-08

Models^*

API mode

Image generation^*

Image input

Yes^*

PDF input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gpt-image-2.5-sunburst-2026-09-08

Models^*

API mode

Image generation^*

Image input

Yes^*

PDF input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gpt-realtime-translate

Models^*

Maximum output

2,000 tokens^*

Maximum input

16,000 tokens^*

API mode

Realtime API^*

Audio input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/anthropic-claude-3-opus

Models^*

Maximum output

1,024 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/anthropic-claude-3.5-haiku

Models^*

Maximum output

1,024 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/anthropic-claude-3.5-sonnet

Models^*

Maximum output

1,024 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/anthropic-claude-3.7-sonnet

Models^*

Maximum output

1,024 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

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

Models^*

Maximum output

8,000 tokens^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/llama3-8b-instruct

Models^*

Maximum output

512 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/llama3.3-70b-instruct

Models^*

Maximum output

2,048 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/mistral-nemo-instruct-2407

Models^*

Maximum output

512 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/openai-o3

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

gradient_ai/openai-o3-mini

Models^*

Maximum output

100,000 tokens^*

Maximum input

200,000 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lemonade/Gemma-3-4b-it-GGUF

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

lemonade/gpt-oss-120b-mxfp-GGUF

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lemonade/gpt-oss-20b-mxfp4-GGUF

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lemonade/Qwen3-4B-Instruct-2507-GGUF

Models^*

Maximum output

32,768 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF

Models^*

Maximum output

32,768 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

llamagate/deepseek-r1-7b-qwen

Models^*

Maximum output

16,384 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

llamagate/deepseek-r1-8b

Models^*

Maximum output

16,384 tokens^*

Maximum input

65,536 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

llamagate/gemma3-4b

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