COMPARE.

01-ai

Yi-Coder-1.5B-Chat

Models

Context window

131,072 tokens

Total parameters

1.48 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

01-ai

Yi-Coder-9B

Models

Context window

131,072 tokens

Total parameters

8.83 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

01-ai

Yi-Coder-9B-Chat

Models

Context window

131,072 tokens

Total parameters

8.83 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

microsoft

AesCode-32B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

62.13 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

AesCode-8B

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

16.33 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ai21.jamba-1-5-large-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

256,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ai21.jamba-1-5-mini-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

256,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ai21.jamba-instruct-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

70,000 tokens^*

API mode

Chat^*

System messages

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/mimo-v2-pro

Models^*

Maximum input

1,000,000 tokens^*

API mode

Chat^*

Prompt caching

Yes^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

aihubmix/muse-spark-1.2

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

amazon

amazon.nova-2-5-sonic

Models^*

API mode

Realtime API^*

Audio input

Yes^*

Audio output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

amazon

amazon.nova-2-sonic-v1:0

Models^*

API mode

Realtime API^*

Audio input

Yes^*

Audio output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

amazon

amazon.rerank-v1:0

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

amazon

amazon.titan-embed-text-v2:0

Models^*

Maximum input

8,192 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anthropic.claude-instant-v1

Models^*

Maximum output

8,191 tokens^*

Maximum input

100,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anthropic.claude-v2:1

Models^*

Maximum output

8,191 tokens^*

Maximum input

100,000 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anyscale/mistralai/Mistral-7B-Instruct-v0.1

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1

Models^*

Maximum output

65,536 tokens^*

Maximum input

65,536 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/Cohere-embed-v3-english

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/Cohere-embed-v3-multilingual

Models^*

Maximum input

512 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/cohere-rerank-v4.0-fast

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/cohere-rerank-v4.0-pro

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

azure_ai/FLUX.2-flex

Models^*

Maximum input

32,000 tokens^*

API mode

Image generation^*

Radar · unrated0/4 core tests · not enough evidence