AI model library — official specs, cutoffs & comparisons · Headless Thrones

1,512 matching models

IBMListed by publisher

granite-3.0-8b-instruct

Granite

Open weights

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

MetaAvailable

Llama 3.2 11B Vision

Llama 3.2 · meta-llama/Llama-3.2-11B-Vision

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023| Llama 3.2-Vision | (Image, text) pairs | 11B (10.6) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 | · month precision

MetaAvailable

Llama 3.2 11B Vision Instruct

Llama 3.2 · meta-llama/Llama-3.2-11B-Vision-Instruct

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023| Llama 3.2-Vision | (Image, text) pairs | 11B (10.6) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 | · month precision

MetaAvailable

Llama 3.2 90B Vision

Llama 3.2 · meta-llama/Llama-3.2-90B-Vision

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023| Llama 3.2-Vision | (Image, text) pairs | 90B (88.8) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 | · month precision

MetaAvailable

Llama 3.2 90B Vision Instruct

Llama 3.2 · meta-llama/Llama-3.2-90B-Vision-Instruct

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023| Llama 3.2-Vision | (Image, text) pairs | 90B (88.8) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 | · month precision

MicrosoftListed by publisher

Phi-3.5-mini-instruct

Phi

Open weights

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

MicrosoftListed by publisher

Phi-3.5-MoE-instruct

Phi

Open weights

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

MetaAvailable

Llama 3.1 405B

Llama 3.1 · meta-llama/Llama-3.1-405B

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Llama 3.1 405B Instruct

Llama 3.1 · meta-llama/Llama-3.1-405B-Instruct

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Llama 3.1 70B

Llama 3.1 · meta-llama/Llama-3.1-70B

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Llama 3.1 70B Instruct

Llama 3.1 · meta-llama/Llama-3.1-70B-Instruct

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Llama 3.1 8B

Llama 3.1 · meta-llama/Llama-3.1-8B

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Llama 3.1 8B Instruct

Llama 3.1 · meta-llama/Llama-3.1-8B-Instruct

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

IBMListed by publisher

granite-20b-code-base-r1.1

Granite

Open weights

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

IBMListed by publisher

granite-20b-code-instruct-r1.1

Granite

Open weights

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

IBMListed by publisher

granite-3b-code-base-128k

Granite

Open weights

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

IBMListed by publisher

granite-3b-code-instruct-128k

Granite

Open weights

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

IBMListed by publisher

granite-8b-code-base-128k

Granite

Open weights

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

IBMListed by publisher

granite-8b-code-instruct-128k

Granite

Open weights

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

IBMListed by publisher

granite-20b-functioncalling

Granite

Open weights

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

Shanghai AI LaboratoryAvailable

AlchemistCoder-CL-7B

AlchemistCoder · AlchemistCoder-CL-7B

Open weights

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

Shanghai AI LaboratoryAvailable

AlchemistCoder-DS-6.7B

AlchemistCoder · AlchemistCoder-DS-6.7B

Open weights

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

MicrosoftListed by publisher

Phi-3-medium-128k-instruct

Phi

Open weights

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

MicrosoftListed by publisher

Phi-3-medium-4k-instruct

Phi

Open weights

Context: 4,000 tokens
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