AI model library — official specs, cutoffs & comparisons

1,512 matching models

QwenAvailable

qwen3.8-omni-flash-realtime

Qwen · qwen3.8-omni-flash-realtime

API

Maximum input: 196,608 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

QwenAvailable

QwQ-32B

QwQ · QwQ-32B

Open weights

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

QwenPreview

QwQ-32B-Preview

QwQ · QwQ-32B-Preview

Open weights

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

Arcee AIListed by publisher

raspberry-3B

raspberry

Open weights

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

GoogleAvailable

recurrentgemma 2b

recurrentgemma · google/recurrentgemma-2b

Open weights

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

GoogleAvailable

recurrentgemma 2b it

recurrentgemma · google/recurrentgemma-2b-it

Open weights

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

GoogleAvailable

recurrentgemma 9b

recurrentgemma · google/recurrentgemma-9b

Open weights

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

GoogleAvailable

recurrentgemma 9b it

recurrentgemma · google/recurrentgemma-9b-it

Open weights

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

Nous ResearchListed by publisher

Redmond-Hermes-Coder

Hermes

Open weights

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

Nous ResearchListed by publisher

Redmond-Puffin-13B

Redmond

Open weights

Context: 4,096 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

RekaAvailable

reka-edge-2603

reka · reka-edge-2603

API / Open weights

Context: 16,384 tokens
Max. output: 16,384 tokens
Knowledge cutoff: Not documented

RekaAvailable

reka-flash-3

reka · reka-flash-3

API / Open weights

Context: 64,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

RekaListed by publisher

reka-flash-3.1

reka · reka-flash-3.1

Open weights

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

OpenBMBAvailable

RLAIF-V-12B

RLAIF · RLAIF-V-12B

Open weights

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

OpenBMBAvailable

RLAIF-V-7B

RLAIF · RLAIF-V-7B

Open weights

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

OpenBMBAvailable

RLHF-V

RLHF · RLHF-V

Open weights

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

OpenBMBAvailable

RLHF-V-SFT

RLHF · RLHF-V-SFT

Open weights

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

OpenBMBAvailable

RLPR-Gemma2-2B-it

RLPR · RLPR-Gemma2-2B-it

Open weights

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

OpenBMBAvailable

RLPR-Llama3.1-8B-Inst

RLPR · RLPR-Llama3.1-8B-Inst

Open weights

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

OpenBMBAvailable

RLPR-Qwen2.5-7B-Base

RLPR · RLPR-Qwen2.5-7B-Base

Open weights

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

StepFunAvailable

RLVR-8B-0926

RLVR · RLVR-8B-0926

Open weights

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

Essential AIListed by publisher

rnj-1

Rnj

Open weights

Context: 32,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Essential AIListed by publisher

rnj-1-instruct

Rnj

Open weights

Context: 32,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Essential AIListed by publisher

rnj-1.5-instruct

Rnj

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