Skip to content
ModelPriceLab

Search model prices

Find source-linked rates by model, vendor, or platform.

Common destinations

All pricesCompare modelsScenario rankings
Vendor Library/Groq/Pricing

Groq API Pricing

Complete pricing for all Groq models. Input/output costs per 1M tokens, context windows, and rate limits.

Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-11.

Groq API Pricing Calculator

Select a model to estimate monthly cost using its listed rates on each channel.

Quick examples:
Input mode
Cache hit rate (share of input tokens served from cache)50%

Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.

Estimated monthly cost at current inputs
ChannelEffective inputOutput /1MEst. / month
groq$0.0000$0.0000$0.0000

Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.

Currently available rates

ALLaM-2-7b

LLMgroq-allam-2-7b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.0000
$0.0000
—
4K
4K
Sources: Groq

Canopy Labs Orpheus Arabic Saudi

Audiogroq-canopylabs-orpheus-arabic-saudi
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
4K
50K
Sources: Groq

Canopy Labs Orpheus V1 English

Audiogroq-canopylabs-orpheus-v1-english
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
4K
50K
Sources: Groq

Compound

LLMgroq-groq-compound
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
131K
8K
Sources: Groq

Compound Mini

LLMgroq-groq-compound-mini
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
131K
8K
Sources: Groq

DeepSeek R1 Distill Llama 70B

LLMgroq-deepseek-r1-distill-70b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M tokens
$0.75
-
$0.99
—
—
—

GPT OSS 120B

LLMgroq-openai-gpt-oss-120b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.15
$0.60
$0.08
131K
66K
Sources: Groq

GPT OSS 20B

LLMgroq-openai-gpt-oss-20b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.08
$0.30
$0.04
131K
66K
Sources: Groq

Llama 3.1 8B

LLMgroq-llama-3.1-8b-instant
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.05
$0.08
—
131K
131K
Sources: Groq

Llama 3.1 8B Instant

LLMgroq-llama-3.1-8b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M tokens
$0.05
-
$0.08
—
—
—

Llama 3.3 70B

LLMgroq-llama-3.3-70b-versatile
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.59
$0.79
—
131K
33K
Sources: Groq

Llama 3.3 70B Versatile

LLMgroq-llama-3.3-70b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M tokens
$0.59
-
$0.79
—
—
—

Llama Prompt Guard 2 22M

LLMgroq-meta-llama-llama-prompt-guard-2-22m
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.03
$0.03
—
1K
1K
Sources: Groq

Mixtral 8x7B

LLMgroq-mixtral-8x7b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M tokens
$0.24
-
$0.24
—
—
—

Prompt Guard 2 86M

LLMgroq-meta-llama-llama-prompt-guard-2-86m
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.04
$0.04
—
1K
1K
Sources: Groq

Qwen3.6 27B

LLMgroq-qwen-qwen3.6-27b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.60
$3.00
$0.30
131K
16K
Sources: Groq

Qwen3.8 27B

LLMgroq-qwen-qwen3.8-27b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.80
$4.00
—
131K
16K
Sources: Groq

Safety GPT OSS 20B

LLMgroq-openai-gpt-oss-safeguard-20b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
$0.08
$0.30
—
131K
66K
Sources: Groq

Whisper

LLMgroq-whisper-large-v3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
—
—
Sources: Groq

Whisper Large V3 Turbo

LLMgroq-whisper-large-v3-turbo
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Groq
global
1M Tokens
-
-
—
—
—
Sources: Groq
Groq Overview
Products, apps, and recent changes
Groq Changes
API changes, pricing updates, and deprecations
AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.

Check my modelsApply for founder pilot