AI model library — official specs, cutoffs & comparisons

1,512 matching models

MicrosoftListed by publisher

Phi-3-small-128k-instruct

Phi

Open weights

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

MicrosoftListed by publisher

Phi-3-small-8k-instruct

Phi

Open weights

Context: 8,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MicrosoftListed by publisher

Phi-3-vision-128k-instruct

Phi

Open weights

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

IBMListed by publisher

granite-20b-code-base-8k

Granite

Open weights

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

IBMListed by publisher

granite-20b-code-instruct-8k

Granite

Open weights

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

IBMListed by publisher

granite-34b-code-base-8k

Granite

Open weights

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

IBMListed by publisher

granite-34b-code-instruct-8k

Granite

Open weights

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

IBMListed by publisher

granite-8b-code-base-4k

Granite

Open weights

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

MetaAvailable

Meta Llama 3 70B

Llama 3 · meta-llama/Meta-Llama-3-70B

Open weights

Context: 8,192 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Meta Llama 3 70B Instruct

Llama 3 · meta-llama/Meta-Llama-3-70B-Instruct

Open weights

Context: 8,192 tokens
Max. output: Not documented
Knowledge cutoff: Dec 2023Knowledge cutoff · month precision

MetaAvailable

Meta Llama 3 8B

Llama 3 · meta-llama/Meta-Llama-3-8B

Open weights

Context: 8,192 tokens
Max. output: Not documented
Knowledge cutoff: Mar 2023Knowledge cutoff · month precision

MetaAvailable

Meta Llama 3 8B Instruct

Llama 3 · meta-llama/Meta-Llama-3-8B-Instruct

Open weights

Context: 8,192 tokens
Max. output: Not documented
Knowledge cutoff: Mar 2023Knowledge cutoff · month precision

OpenBMBAvailable

MiniCPM-1B-sft-bf16

MiniCPM · MiniCPM-1B-sft-bf16

Open weights

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

OpenBMBAvailable

UltraLM-13b-v2.0

UltraLM · UltraLM-13b-v2.0

Open weights

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

ByteDance SeedAvailable

academic-ds-9B

academic · academic-ds-9B

Open weights

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

NVIDIAListed by publisher

AceMath-RL-Nemotron-7B

Nemotron

Open weights

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

NVIDIAListed by publisher

AceReason-Nemotron-14B

Nemotron

Open weights

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

NVIDIAListed by publisher

AceReason-Nemotron-7B

Nemotron

Open weights

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

Arcee AIListed by publisher

AFM-4.5B

AFM

Open weights

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

Arcee AIListed by publisher

AFM-4.5B-Base

AFM

Open weights

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

Arcee AIListed by publisher

AFM-4.5B-ov

AFM

Open weights

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

Arcee AIListed by publisher

AFM-4.5B-Preview

AFM

Open weights

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

Shanghai AI LaboratoryAvailable

Agent-FLAN-7b

Agent · Agent-FLAN-7b

Open weights

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

OpenBMBAvailable

AgentCPM-Explore

AgentCPM · AgentCPM-Explore

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