Skip to content
HomeGroqAll changesPrompt Caching feature added
Groq
Pricing changePlan removedNew planFeature addedJul 4 → Oct 5, 2025

Groq Removes Multiple Models While Adding High-Performance GPT OSS 20B and 120B with New Prompt Caching Feature

AI & Machine LearningDirection: down
The changePrompt Caching feature added
BeforeJul 4Not listed
AfterOct 5Prompt Caching feature
added
13 changes2 capturesJul 4, 2025 → Oct 5, 2025

What happened

Between the Jul 4, 2025 and Oct 5, 2025 captures of Groq's pricing page, Pulse recorded 13 changes: Gemma 2 9B 8k model removed (previously $0.20 input/$0.20 output per million tokens); Llama Guard 3 8B 8k model removed (previously $0.20 input/$0.20 output per million tokens); GPT OSS 20B 128k model added at $0.10 input/$0.50 output per million tokens with 1,000 TPS; Kimi K2-0905 1T 256k model added at $1.00 input/$3.00 output per million tokens with 200 TPS; GPT OSS 120B 128k model added at $0.15 input/$0.75 output per million tokens with 500 TPS; DeepSeek R1 Distill Llama 70B 128k model removed (previously $0.75 input/$0.99 output per million tokens); Prompt Caching feature added with 50% discount on cached input tokens for select models (Kimi K2, GPT OSS 20B, GPT OSS 120B); Mistral Saba 24B 32k model removed (previously $0.79 input/$0.79 output per million tokens); Llama 3 8B 8k model removed (previously $0.05 input/$0.08 output per million tokens); Distil-Whisper ASR model removed (previously $0.02 per hour transcribed with 250x speed factor); Llama 3 70B 8k model removed (previously $0.59 input/$0.79 output per million tokens); Batch API discount increased from 25% to 50%; Qwen QwQ 32B (Preview) 128k model removed (previously $0.29 input/$0.39 output per million tokens). Pulse files it as a pricing change (plan removed, new plan, feature added, discount change) with a downward direction. Pulse's latest capture (Nov 18, 2026) lists GPT OSS 20B at $0.08 per 1M input tokens + $0.30 per 1M output tokens, Whisper Large v3 (ASR) at $0.11 per hour transcribed, Whisper Large V3 Turbo (ASR) at $0.04 per hour transcribed, Canopy Labs Orpheus Arabic Saudi (TTS) at $40 per 1M characters and Canopy Labs Orpheus V1 English (TTS) at $22 per 1M characters.

Groq's previous recorded change was "Groq Introduces Llama 4 Maverick and Qwen3 Models Amid Removal of Multiple High-Cost Plans and End of 50% Batch Processing Discount" (Q2 2025). Groq has been tracked since 2024-11-17.

In the same window Anthropic also changed their AI & Machine Learning pricing pages. Those moves are listed further down, and the Pulse Agent can compare them side by side.

  • —Plan
    Plan removed

    Gemma 2 9B 8k model removed (previously $0.20 input/$0.20 output per million tokens)

  • —Plan
    Plan removed

    Llama Guard 3 8B 8k model removed (previously $0.20 input/$0.20 output per million tokens)

  • GPT OSS 20BPlan
    Added

    BeforeNot listed

    AfterGPT OSS 20B 128k model ($0.10)

  • —Plan
    Added

    BeforeNot listed

    AfterKimi K2-0905 1T 256k model ($1.00)

  • GPT OSS 120BPlan
    Added

    BeforeNot listed

    AfterGPT OSS 120B 128k model ($0.15)

  • —Plan
    Plan removed

    DeepSeek R1 Distill Llama 70B 128k model removed (previously $0.75 input/$0.99 output per million tokens)

  • GPT OSS 20B, GPT OSS 120BFeature
    Added
    Not listedPrompt Caching feature
  • —Plan
    Plan removed

    Mistral Saba 24B 32k model removed (previously $0.79 input/$0.79 output per million tokens)

  • —Plan
    Plan removed

    Llama 3 8B 8k model removed (previously $0.05 input/$0.08 output per million tokens)

  • —Plan
    Plan removed

    Distil-Whisper ASR model removed (previously $0.02 per hour transcribed with 250x speed factor)

  • —Plan
    Plan removed

    Llama 3 70B 8k model removed (previously $0.59 input/$0.79 output per million tokens)

  • —Discount
    +25 percentage points
    25%50%
  • —Plan
    Plan removed

    Qwen QwQ 32B (Preview) 128k model removed (previously $0.29 input/$0.39 output per million tokens)

Values as written on Groq's public pricing page in the two captures Pulse compared; where the page states no number, the cells give the wording before and after.

Evidence

The two captures Pulse compared

Full-page captures of Groq's pricing page (groq.com) from Jul 4, 2025 and Oct 5, 2025; the change is marked on the page, where Prompt Caching feature now appears.

Sign in to see the evidence

The two full-page captures with this change marked up are free with an account.

Groq, the last 90 days

Full history
  1. Jul 2, 2026ImprovementGroq: Qwen 3.6 27B added, new Enterprise-only LLM tier + 1 more change
  2. Jan 10, 2026Price decreaseGroq Reduces GPT OSS 20B Input and Output Token Prices by 25% and 40%, Enhancing Cost Efficiency for Users
  3. Week of Dec 22, 2025PackagingGroq swaps PlayAI for Orpheus TTS, cuts text-to-speech price 56%
  4. Q3 2025PackagingGroq Removes Multiple Models While Adding High-Performance GPT OSS 20B and 120B with New Prompt Caching Feature This change
  5. Q2 2025PackagingGroq Introduces Llama 4 Maverick and Qwen3 Models Amid Removal of Multiple High-Cost Plans and End of 50% Batch Processing Discount

Across AI & Machine Learning in the same window

All AI & Machine Learning changes
  1. AnthropicJan 10Anthropic API Introduces Tiered Pricing and Prompt Caching for Sonnet 4.5, Restructuring Costs Based on Token Length
  2. AnthropicJan 10Anthropic API Introduces Code Execution Tool with 50 Free Hours Daily, Enhancing Service Offerings and Flexibility for Users
  3. AnthropicJan 10Anthropic API Cuts Flagship Opus Model Prices by 67% in Major Update to Version 4.5, Launching New Pricing Structure
  4. AnthropicJan 10Anthropic Max Plan Now Includes Memory Across Conversations, Enhancing User Experience and Functionality
  5. AnthropicJan 10Anthropic Introduces Max Plan at $100+/Month, Offering 5x-20x More Usage Than Pro Plan

Questions about this change

Did Groq raise prices in October 2025?

No list-price increase was recorded between Jul 4, 2025 and Oct 5, 2025. The change Pulse detected was a pricing change: plan removed, new plan, feature added, discount change.

What changed on Groq's pricing page between Jul 4, 2025 and Oct 5, 2025?

Gemma 2 9B 8k model removed (previously $0.20 input/$0.20 output per million tokens); Llama Guard 3 8B 8k model removed (previously $0.20 input/$0.20 output per million tokens); GPT OSS 20B plan added: GPT OSS 20B 128k model ($0.10); plan added: Kimi K2-0905 1T 256k model ($1.00); GPT OSS 120B plan added: GPT OSS 120B 128k model ($0.15); DeepSeek R1 Distill Llama 70B 128k model removed (previously $0.75 input/$0.99 output per million tokens); GPT OSS 20B, GPT OSS 120B feature added: Prompt Caching feature; Mistral Saba 24B 32k model removed (previously $0.79 input/$0.79 output per million tokens); Llama 3 8B 8k model removed (previously $0.05 input/$0.08 output per million tokens); Distil-Whisper ASR model removed (previously $0.02 per hour transcribed with 250x speed factor); Llama 3 70B 8k model removed (previously $0.59 input/$0.79 output per million tokens); discount: 25% → 50% (+25 pts); Qwen QwQ 32B (Preview) 128k model removed (previously $0.29 input/$0.39 output per million tokens). Pulse compared the captures it took on Jul 4, 2025 and Oct 5, 2025; the before/after table above lists each item as written on the page.

How often does Groq change its pricing?

Pulse recorded 1 other pricing-page change for Groq in the 90 days before this one; the previous change was "Groq Introduces Llama 4 Maverick and Qwen3 Models Amid Removal of Multiple High-Cost Plans and End of 50% Batch Processing Discount" in Q2 2025; Groq has been tracked since 2024-11-17.

Groq Removes Multiple Models While Adding High-Performance GPT OSS 20B and 120B with New Prompt Caching Feature — Oct 5, 2025 · PricingSaaS Pulse