COMPARE.

Unspecified

cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/cloudflare/clef-omni

Models^*

Maximum input

64,000 tokens^*

API mode

Evaluation service^*

Image input

Yes^*

Video input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/google/gemma-2b-it-lora

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/google/gemma-7b-it-lora

Models^*

Maximum output

3,500 tokens^*

Maximum input

3,500 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-2-7b-chat-fp16

Models^*

Maximum output

3,072 tokens^*

Maximum input

3,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-2-7b-chat-int8

Models^*

Maximum output

2,048 tokens^*

Maximum input

2,048 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8

Models^*

Maximum output

32,000 tokens^*

Maximum input

32,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-3.2-1b-instruct

Models^*

Maximum output

60,000 tokens^*

Maximum input

60,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-3.2-3b-instruct

Models^*

Maximum output

80,000 tokens^*

Maximum input

80,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/meta/llama-guard-3-8b

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/mistral/mistral-7b-instruct-v0.1

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora

Models^*

Maximum output

15,000 tokens^*

Maximum input

15,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/@hf/thebloke/codellama-7b-instruct-awq

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cloudflare/clef-omni

Models^*

Maximum input

64,000 tokens^*

API mode

Evaluation service^*

Image input

Yes^*

Video input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

zai

codegeex4-all-9b

Models

Context window

131,072 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

17.51 GiB

Radar · unrated0/4 core tests · not enough evidence

zai

cogagent-9b-20241220

Models

Context window

8,192 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

25.90 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cohere.command-light-text-v14

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cohere.command-text-v14

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cohere.rerank-v3-5:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cohere/embed-v5.0-fast

Models^*

Maximum input

128,000 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

cohere/embed-v5.0-pro

Models^*

Maximum input

128,000 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

cohere

command-a-plus-05-2026-bf16

Models

Context window

200,000 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

407.45 GiB

Radar · unrated0/4 core tests · not enough evidence