fineprint what AI companies quietly changed · RSS

2026-09-24 18:22 UTC · groq/models · live page

2 line(s) added, 16 removed (around "Groq Compound").

Summary by fallback. It may be wrong; the diff below is what actually changed. Raw: 04aa918878-groq-models.diff · commit 04aa918878

diff --git a/snapshots/groq/models.md b/snapshots/groq/models.mdindex 1c6fe2a..e5c8a21 100644--- a/snapshots/groq/models.md+++ b/snapshots/groq/models.md@@ -9,16 +9,4 @@ Log In Explore all available models on GroqCloud. -### Groq Compound--Groq Compound is an AI system powered by openly available models that intelligently and selectively uses built-in tools to answer user queries, including web search and code execution.--Token Speed--~450 tps--Modalities--Capabilities- ### OpenAI GPT-OSS 120B @@ -42,16 +30,5 @@ Note: Production models are intended for use in your production environments. Th | GPT OSS 20Bopenai/gpt-oss-20b | 1000 | $0.075 input$0.30 output | 250K TPM1K RPM | 131,072 | 65,536 | - | | Whisperwhisper-large-v3 | - | $0.111 per hour | 200K ASH300 RPM | - | - | 100 MB |-| Whisper Large V3 Turbowhisper-large-v3-turbo | - | $0.04 per hour | 400K ASH400 RPM | - | - | - |--Systems are a collection of models and tools that work together to answer a user query.--| MODEL ID | SPEED (T/SEC) | PRICE PER 1M TOKENS | RATE LIMITS (DEVELOPER PLAN) | CONTEXT WINDOW (TOKENS) | MAX COMPLETION TOKENS | MAX FILE SIZE |-|---|---|---|---|---|---|---|-| Compoundgroq/compound | 450 | - | 200K TPM200 RPM | 131,072 | 8,192 | - |-| Compound Minigroq/compound-mini | 450 | - | 200K TPM200 RPM | 131,072 | 8,192 | - |--Learn More About Agentic Tooling--Discover how to build powerful applications with real-time web search and code execution+| Whisper Large V3 Turbowhisper-large-v3-turbo | - | $0.04 per hour | 400K ASH400 RPM | - | - | 100 MB |  Note: Preview models are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice. Read more about deprecations here.@@ -65,6 +42,5 @@ Note: Preview models are intended for evaluation purposes only and should not be | MiniMax M2.7Enterpriseminimaxai/minimax-m2.7 | 260 | ContactSales | ContactSales | 196,608 | 131,072 | - | | Safety GPT OSS 20Bopenai/gpt-oss-safeguard-20b | 1000 | $0.075 input$0.30 output | 150K TPM1K RPM | 131,072 | 65,536 | - |-| Qwen/Qwen3.6-27Bqwen/qwen3.6-27b | 500 | $0.60 input$3.00 output | 250K TPM1K RPM | 131,072 | 16,384 | 20 MB |-| Qwen/Qwen3.8-27Bqwen/qwen3.8-27b | 450 | $0.80 input$4.00 output | 250K TPM1K RPM | 131,042 | 16,384 | 20 MB |+| Qwen/Qwen3.8-27Bqwen/qwen3.8-27b | 450 | $0.80 input$4.00 output | 250K TPM1K RPM | 131,072 | 16,384 | 20 MB |  Deprecated models are models that are no longer supported or will no longer be supported in the future. See our deprecation guidelines and deprecated models here.

← Groq timeline