Skip to content

AI models as each provider exposes them

Context window, maximum output, price and prompt caching for 6,186 entries. Built on models.dev, with 67 entries corrected or evaluated by providers.dev.

333 providers, 18 by subscription466 models86 cache evaluationsUpdated 2026-11-17

6 entries

This view as JSON/api/v1/entries?provider=runcrate&sort=verified&order=desc

Provider-model entries
Input window Cache lifetime
Qwen3.8 Flash
Qwen/Qwen3.8-Flash
Runcrate 1Mdocumented 1M 131K $0.1187 / $0.4011 2026-08-26 ShortUnknownLongUnknown models.dev2026-11-17
DeepSeek V4.1 Flash
deepseek-ai/DeepSeek-V4.1-Flash
Runcrate 1.05Mdocumented 1.05M 384K $0.147 / $0.441 2026-09-10 ShortUnknownLongUnknown models.dev2026-11-17
DeepSeek V4.1 Flash 1017
deepseek-ai/DeepSeek-V4.1-Flash-1017
Runcrate 1.05Mdocumented 1.05M 384K $0.1029 / $0.3087 2026-10-17 ShortUnknownLongUnknown models.dev2026-11-17
Kimi K2.6
moonshotai/Kimi-K2.6
Runcrate 262Kdocumented 262K 16.38K $0.7875 / $3.675 2026-04-20 ShortUnknownLongUnknown models.dev2026-11-17
GLM-5.3
zai-org/GLM-5.3
Runcrate 1.05Mdocumented 1.05M 131K $0.5906 / $2.625 2026-08-14 ShortUnknownLongUnknown models.dev2026-11-17
GLM-5.3-Flash
zai-org/GLM-5.3-Flash
Runcrate 1.05Mdocumented 1.05M 131K $0.1575 / $0.525 2026-08-26 ShortUnknownLongUnknown models.dev2026-11-17