COMPARE.

Unspecified

together_ai/mistralai/Mistral-7B-Instruct-v0.3

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/moonshotai/Kimi-K2.5-fp4

Models^*

Maximum input

262,144 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/together/Tev1-4B-experimental

Models^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together_ai/togethercomputer/CodeLlama-34b-Instruct

Models^*

Tool calling

Yes^*

API mode

Chat^*

Parallel tool calls

Yes^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

together-ai-8.1b-21b

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

transcribe/StartTranscriptionJob

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

tts-1

Models^*

API mode

Speech synthesis^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

tts-1-hd

Models^*

API mode

Speech synthesis^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

typesafe/jev-1.13.0

Models^*

Maximum input

65,536 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

typesafe/jev-latest

Models^*

Maximum input

65,536 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/chirp_2

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/chirp_3

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemini-3.5-transcribe

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemini-3.5-transcribe-live

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/gemma-4-26b-a4b-it

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-default

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-default-002

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-default-003

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-default-004

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-default@latest

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-fast

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-fast-004

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

vertex_ai/semantic-ranker-fast@latest

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/whisper-large-v3-turbo

Models^*

API mode

Audio transcription^*

Radar · unrated0/4 core tests · not enough evidence