AI model library — official specs, cutoffs & comparisons

79 matching models

IBMListed by publisher

granite-switch-4.1-30b

Granite

Open weights

Context: 131,072 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-switch-4.1-8b

Granite

Open weights

Context: 131,072 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.2-30b

Granite

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.2-3b

Granite

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.2-8b

Granite

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-swash-2b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-swash-3b-a600m

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-switch-4.1-30b-preview

Granite

Open weights

Context: 131,072 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-switch-4.1-3b-preview

Granite

Open weights

Context: 131,072 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-switch-4.1-8b-preview

Granite

Open weights

Context: 131,072 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-30b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-30b-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-3b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-3b-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-8b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.1-8b-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-vision-4.1-4b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-3b-vision

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-1b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-1b-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-350m

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-350m-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-h-1b

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

IBMListed by publisher

granite-4.0-h-1b-base

Granite

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

Go beyond the spec sheet

The decisions behind the numbers.

Source-checked guides to pricing, usable context, and access restrictions.

Claude Sonnet 4.6 pricing: API costs, caching and real workload math GPT-5.4 context window: the 1.05M limit, output budget and cost threshold Gemini 2.5 Pro context window: input limits, access and long-document costs GPT-5.4 mini context window: 400K capacity and practical task budgets