COMPARE.

Unspecified

deepinfra/Qwen/Qwen3.5-35B-A3B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Qwen/Qwen3.5-397B-A17B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Qwen/Qwen3.8-2.4T-A95B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Qwen/Qwen3.8-27B

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/tencent/Hy3

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/thinkingmachines/Inkling

Models^*

Maximum input

524,288 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/thinkingmachines/Inkling-Small

Models^*

Maximum input

524,288 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/XiaomiMiMo/MiMo-V2.5

Models^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/XiaomiMiMo/MiMo-V2.5-Pro

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-4.6

Models^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-4.7

Models^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-4.7-Flash

Models^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-5

Models^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-5.1

Models^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/zai-org/GLM-5.2

Models^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepseek/deepseek-coder

Models^*

Maximum output

4,096 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

eu.anthropic.claude-3-opus-20240229-v1:0

Models^*

Maximum output

4,096 tokens^*

Maximum input

200,000 tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

eu.twelvelabs.marengo-embed-2-7-v1:0

Models^*

Maximum input

77 tokens^*

API mode

Embeddings^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/accounts/fireworks/models/deepseek-v4-flash

Models^*

Maximum output

384,000 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/accounts/fireworks/models/glm-5p1

Models^*

Maximum output

131,072 tokens^*

Maximum input

202,752 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/accounts/fireworks/models/gpt-oss-20b

Models^*

Maximum output

32,768 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/accounts/fireworks/models/qwen3p7-plus

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/accounts/fireworks/routers/glm-5p1-fast

Models^*

Maximum output

131,072 tokens^*

Maximum input

202,800 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

fireworks_ai/deepseek-v4-flash

Models^*

Maximum output

384,000 tokens^*

Maximum input

1,048,576 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence