AI model library — official specs, cutoffs & comparisons

1,512 matching models

Shanghai AI LaboratoryAvailable

CapRL-3B

CapRL · CapRL-3B

Open weights

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

Shanghai AI LaboratoryAvailable

CapRL-InternVL3.5-8B

CapRL · CapRL-InternVL3.5-8B

Open weights

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

Shanghai AI LaboratoryAvailable

CapRL-Qwen3VL-2B

CapRL · CapRL-Qwen3VL-2B

Open weights

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

Shanghai AI LaboratoryAvailable

CapRL-Qwen3VL-4B

CapRL · CapRL-Qwen3VL-4B

Open weights

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

OpenAIAvailable

Chat Latest

GPT · chat-latest

API

Context: 400,000 tokens
Max. output: 128,000 tokens
Knowledge cutoff: Apr 20, 2026Knowledge cutoff · day precision

Z.aiAvailable

chatglm-6b

ChatGLM · chatglm-6b

Open weights

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

Z.aiAvailable

chatglm2-6b

ChatGLM · chatglm2-6b

Open weights

Context: 32K tokens (8K dialogue-alignment training)
Max. output: Not documented
Knowledge cutoff: Not documented

Z.aiAvailable

chatglm2-6b-32k

ChatGLM · chatglm2-6b-32k

Open weights

Context: 32K tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Z.aiAvailable

chatglm3-6b

ChatGLM · chatglm3-6b

Open weights

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

Z.aiAvailable

chatglm3-6b-128k

ChatGLM · chatglm3-6b-128k

Open weights

Context: 128K tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Z.aiAvailable

chatglm3-6b-32k

ChatGLM · chatglm3-6b-32k

Open weights

Context: 32K tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Z.aiAvailable

chatglm3-6b-base

ChatGLM · chatglm3-6b-base

Open weights

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

Z.aiAvailable

codegeex2-6b

CodeGeeX · codegeex2-6b

Open weights

Context: 8,192 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Z.aiAvailable

codegeex4-all-9b

CodeGeeX · codegeex4-all-9b

Open weights

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

GoogleAvailable

codegemma 1.1 2b

codegemma · google/codegemma-1.1-2b

Open weights

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

GoogleAvailable

codegemma 1.1 7b it

codegemma · google/codegemma-1.1-7b-it

Open weights

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

GoogleAvailable

codegemma 2b

codegemma · google/codegemma-2b

Open weights

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

GoogleAvailable

codegemma 7b

codegemma · google/codegemma-7b

Open weights

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

GoogleAvailable

codegemma 7b it

codegemma · google/codegemma-7b-it

Open weights

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

MetaAvailable

CodeLlama 13b hf

Code Llama · meta-llama/CodeLlama-13b-hf

Open weights

Context: 100,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MetaAvailable

CodeLlama 13b Instruct hf

Code Llama · meta-llama/CodeLlama-13b-Instruct-hf

Open weights

Context: 100,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MetaAvailable

CodeLlama 13b Python hf

Code Llama · meta-llama/CodeLlama-13b-Python-hf

Open weights

Context: 100,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MetaAvailable

CodeLlama 34b hf

Code Llama · meta-llama/CodeLlama-34b-hf

Open weights

Context: 100,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MetaAvailable

CodeLlama 34b Instruct hf

Code Llama · meta-llama/CodeLlama-34b-Instruct-hf

Open weights

Context: 100,000 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