COMPARE.

Unspecified

mistral/voxtral-mini-realtime-2602

Models^*

API mode

Audio transcription^*

Audio input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-mini-realtime-latest

Models^*

API mode

Audio transcription^*

Audio input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-mini-transcribe-realtime-2602

Models^*

API mode

Audio transcription^*

Audio input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-mini-transcribe-realtime-latest

Models^*

API mode

Audio transcription^*

Audio input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-mini-tts-2603

Models^*

API mode

Speech synthesis^*

Audio output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

mistral/voxtral-mini-tts-latest

Models^*

API mode

Speech synthesis^*

Audio output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

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

Models^*

Maximum input

979,000 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/meta-llama/Llama-Guard-3-8B

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nebius/Qwen/Qwen3.8-27B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/baai/bge-m3

Models^*

Maximum output

96,000 tokens^*

Maximum input

8,192 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/baai/bge-reranker-v2-m3

Models^*

Maximum output

8,000 tokens^*

Maximum input

8,000 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-embedding-0.6b

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-embedding-8b

Models^*

Maximum output

4,096 tokens^*

Maximum input

32,768 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-reranker-8b

Models^*

Maximum output

4,096 tokens^*

Maximum input

32,768 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.embed-english-light-v3.0

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.embed-english-v3.0

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.embed-multilingual-light-v3.0

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.embed-multilingual-v3.0

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/codegemma

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/codellama

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama2

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama2-uncensored

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama2:13b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama2:70b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence