Provider pricing hub

Groq API Pricing and Models

GroqCloud models for low-latency inference and token cost planning.

Use calculator View model pricing Open provider website

Pricing summary

Groq pricing at a glance

These facts are derived from the canonical provider models currently available to CostRivo.

Models tracked

Cached-price models

Context window range

131,072 tokens

Latest verification

Jul 20, 2026

Model pricing

Groq models

Compare provider models with the same pricing unit before opening a model-specific calculator.

Swipe sideways to see all columns.

Canonical model pricing and verified model facts for this provider
Model	Input price	Output price	Cached input	Context window	Capabilities	Verification	Action
GPT OSS 20B GPT OSS	$0.075 / 1M tokens	$0.30 / 1M tokens	Not available	131,072 tokens	text, reasoning	GroqGPT OSS 20B 128kStable Official source Verified Jul 13, 2026. Estimates vary by usage and provider pricing conditions.	Open model
Safety GPT OSS 20B GPT OSS	$0.075 / 1M tokens	$0.30 / 1M tokens	Not available	131,072 tokens	text, reasoning	GroqGPT OSS Safeguard 20BStable Official source Verified Jul 13, 2026. Estimates vary by usage and provider pricing conditions.	Open model
GPT OSS 120B GPT OSS	$0.15 / 1M tokens	$0.60 / 1M tokens	Not available	131,072 tokens	text, reasoning	GroqGPT OSS 120B 128kStable Official source Verified Jul 13, 2026. Estimates vary by usage and provider pricing conditions.	Open model
Llama 3.3 70B Llama 3.3	$0.59 / 1M tokens	$0.79 / 1M tokens	Not available	131,072 tokens	text	GroqLlama 3.3 70B Versatile 128kStable Official source Verified Jul 20, 2026. Estimates vary by usage and provider pricing conditions.	Open model
Llama 3.1 8B Llama 3.1	$0.05 / 1M tokens	$0.08 / 1M tokens	Not available	131,072 tokens	text	GroqLlama 3.1 8B Instant 128kStable Official source Verified Jul 20, 2026. Estimates vary by usage and provider pricing conditions.	Open model
Qwen/Qwen3.6-27B Qwen 3.6	$0.60 / 1M tokens	$3.00 / 1M tokens	Not available	131,072 tokens	text, reasoning	GroqQwen 3.6 27B 131kStable Official source Verified Jul 20, 2026. Estimates vary by usage and provider pricing conditions.	Open model

Price-derived model highlights

Each criterion is calculated independently from eligible, verified Groq token pricing. The same model may lead more than one criterion.

Lowest input price

Llama 3.1 8B

$0.05 / 1M

Lowest listed cost for 1M input tokens.

View model pricing

Lowest output price

Llama 3.1 8B

$0.08 / 1M

Lowest listed cost for 1M output tokens.

View model pricing

Lowest combined token price

Llama 3.1 8B

$0.13 total

Cost of 1M input tokens plus 1M output tokens.

View model pricing

Calculator

Estimate Groq API cost

Groq is preselected with GPT OSS 20B as the starting model.

Model selection

Choose the provider and model you want to estimate.

ProviderModel

GroqGPT OSS 20B 128k

Input price

$0.075 / 1M tokens

Output price

$0.30 / 1M tokens

GroqGPT OSS 20B 128kStable

Official source

Verified Jul 13, 2026. Estimates vary by usage and provider pricing conditions.

Usage assumptions

Estimate traffic and token usage for an average request.

UsersActive seats, customers, or internal users.

Requests per dayAverage AI calls per user each day.

Input tokensPrompt, history, and retrieved context per request.

Output tokensGenerated answer length; SaaS founders should test long replies.

Days per monthUse 30 for always-on products or fewer for batch jobs.

Estimated results

Run the calculator to see projected cost and usage volume.

Enter your usage details, then select Calculate estimate to see your projected cost.

Estimated cost = input usage cost + output usage cost + supported optional charges.

Reviewed starting points

Recommended models

These Groq selections use reviewed catalog capabilities and compatible verified pricing. Each label reflects the evidence shown in the catalog below.

Reasoning

GPT OSS 20B

ReasoningVerified token pricing

Listed in the reviewed reasoning catalog category.

Use calculator

Lowest combined price

Llama 3.1 8B

GenerativeVerified token pricing

Lowest combined verified token price among compatible generation models.

Use calculator

Vision

Llama 4 Scout 17B 16E

GenerativeCatalog details only

Reviewed metadata lists image input support.

View model details

Safety

Safety GPT OSS 20B

SafetyVerified token pricing

Listed in a reviewed safety or moderation catalog category.

Use calculator

Model catalog

Groq model catalog

Calculator actions appear only for exact model IDs with compatible verified token pricing.

8 currentReviewed Jul 15, 2026Official catalog source

8 of 8 models

Filters

Reasoning

GPT OSS 20B

openai/gpt-oss-20b

GPT OSS

ReasoningStableAPI available

OpenAI open-weight reasoning model hosted on GroqCloud with browser search and code execution support.

Context: 131,072 tokens
Maximum output: 65,536 tokens
Input: Text
Output: Text
Model owner: OpenAI
Host provider: Groq
Speed: 1,000 tokens/second
Rate limits: 250,000 TPM, 1,000 RPM

Capabilities

ReasoningBrowser SearchCode ExecutionFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.075 input / $0.3 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

GPT OSS 120B

openai/gpt-oss-120b

GPT OSS

ReasoningStableAPI available

OpenAI flagship open-weight 120B model hosted on GroqCloud with reasoning and built-in tool support.

Context: 131,072 tokens
Maximum output: 65,536 tokens
Input: Text
Output: Text
Model owner: OpenAI
Host provider: Groq
Speed: 500 tokens/second
Rate limits: 250,000 TPM, 1,000 RPM

Capabilities

ReasoningBrowser SearchCode ExecutionFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.15 input / $0.6 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

Qwen3-32B

qwen/qwen3-32b

Qwen3

ReasoningPreviewAPI available

Preview Qwen3 reasoning model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 40,960 tokens
Input: Text
Output: Text
Model owner: Qwen
Host provider: Groq
Speed: 400 tokens/second
Rate limits: 300,000 TPM, 1,000 RPM

Capabilities

ReasoningFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Catalog details only

No compatible public calculator price is listed.

Official sourceVerified Jul 14, 2026

Qwen/Qwen3.6-27B

qwen/qwen3.6-27b

Qwen 3.6

ReasoningPreviewAPI available

Preview Qwen 3.6 27B model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 32,768 tokens
Input: Text
Output: Text
Model owner: Qwen
Host provider: Groq
Speed: 500 tokens/second
Rate limits: 250,000 TPM, 1,000 RPM

Capabilities

ReasoningFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.6 input / $3 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

Generative

Llama 4 Scout 17B 16E

meta-llama/llama-4-scout-17b-16e-instruct

Llama 4

GenerativePreviewAPI available

Preview multimodal Llama 4 Scout model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 8,192 tokens
Input: Text, Image
Output: Text
Model owner: Meta
Host provider: Groq
Speed: 750 tokens/second
Rate limits: 300,000 TPM, 1,000 RPM

Capabilities

VisionMultimodalFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Catalog details only

No compatible public calculator price is listed.

Official sourceVerified Jul 14, 2026

Llama 3.3 70B

llama-3.3-70b-versatile

Llama 3.3

GenerativeStableAPI available

Production Llama 3.3 70B general-purpose model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 32,768 tokens
Input: Text
Output: Text
Model owner: Meta
Host provider: Groq
Speed: 280 tokens/second
Rate limits: 300,000 TPM, 1,000 RPM

Capabilities

Text GenerationFunction CallingStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.59 input / $0.79 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

Llama 3.1 8B

llama-3.1-8b-instant

Llama 3.1

GenerativeStableAPI available

Production low-latency Llama 3.1 8B model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 131,072 tokens
Input: Text
Output: Text
Model owner: Meta
Host provider: Groq
Speed: 560 tokens/second
Rate limits: 250,000 TPM, 1,000 RPM

Capabilities

Text GenerationLow LatencyFunction Calling

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.05 input / $0.08 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

Safety

Safety GPT OSS 20B

openai/gpt-oss-safeguard-20b

GPT OSS

SafetyPreviewAPI available

Preview safety-focused GPT OSS model hosted on GroqCloud.

Context: 131,072 tokens
Maximum output: 65,536 tokens
Input: Text
Output: Text
Model owner: OpenAI
Host provider: Groq
Speed: 1,000 tokens/second
Rate limits: 150,000 TPM, 1,000 RPM

Capabilities

Content SafetyReasoningStructured Outputs

Endpoints

Chat CompletionsResponses Compatible

Deployment

Groqcloud Api

Verified token pricing

$0.075 input / $0.3 output per 1M tokens

Use calculator

Official sourceVerified Jul 14, 2026

Pricing sources

Pricing source and update notes

CostRivo shows official source references and verification metadata where available. Review provider pricing pages before making high-volume purchasing decisions.

Official provider pricing

Open Groq pricing references for current provider terms, tiers, and availability notes.

Open source

Pricing table

Review CostRivo's cross-provider pricing table, verification dates, source links, and lifecycle labels.

Open source

FAQ

Groq cost planning questions

Short answers for using this provider calculator.

How is Groq API cost calculated?

The calculator multiplies input, output, and cached input tokens by the selected model pricing, then scales the result by request volume.

Which Groq models have the lowest tracked token prices?

Lowest input price: Llama 3.1 8B at $0.05 per 1M tokens; Lowest output price: Llama 3.1 8B at $0.08 per 1M tokens; Lowest combined token price: Llama 3.1 8B at $0.13 for 1M input plus 1M output tokens. Each criterion is calculated independently from eligible verified token prices.

Does this estimate include cached input pricing?

Cached input pricing is not listed for the current provider models in this data set.

When was Groq pricing last verified?

The most recent model verification shown by CostRivo is Jul 20, 2026. Individual model rows retain their own source and verification details.

Pricing updates

Get pricing updates

Get notified when AI model prices change, new providers are added, product updates ship, launch notes go out, or Costrivo introduces future premium planning features.

No spam. Pricing and product updates only. We only store your email, this page, and signup time.