Groq API pricing, checked at the source
Prices for the models on GroqCloud, read off Groq's own model docs with a link on every row. Estimate a monthly bill below, with batch.
Groq API prices per 1M tokens
Standard prices in USD. Each row links to Groq's pricing page and shows the day we checked it.
| Model | Input | Cached input | Output | Batch API (in / out) | Notes | Source |
|---|---|---|---|---|---|---|
| GPT OSS 120B | $0.15 | $0.075 | $0.60 | $0.075 / $0.30 | Sourcechecked 2026-10-25 | |
| GPT OSS 20B | $0.075 | $0.037 | $0.30 | $0.0375 / $0.15 | Sourcechecked 2026-10-25 | |
| Safety GPT OSS 20BPreview | $0.075 | none listed | $0.30 | $0.0375 / $0.15 | Prompt caching docs say cached input is 50% off for this model; no cached price was read off its page. | Sourcechecked 2026-10-25 |
| Qwen/Qwen3.8-27BPreview | $0.80 | none listed | $4.00 | $0.40 / $2.00 | Sourcechecked 2026-10-25 |
Terms on this page: Token · Prompt caching · Context window · Batch API
Estimate your Groq bill
Enter your monthly tokens and how they split between new input, cached input and output. The result updates as you type.
Write 40k, 250M or 5B. Input, cached input and output tokens together.
100M tokens a month costs from $6.42 (GPT OSS 20B) to $96.00 (Qwen/Qwen3.8-27B).
| Model | Per month | Per 1M tokens at this split |
|---|---|---|
| GPT OSS 20B | $6.42 | $0.06421 |
| Safety GPT OSS 20BPreview | $8.63 | $0.08625 |
| GPT OSS 120B | $12.90 | $0.129 |
| Qwen/Qwen3.8-27BPreview | $96.00 | $0.96 |
Standard prices in USD on 2026-10-25, before tax. Long-prompt tiers are left out; see the price table.
Groq speech to text prices
Prices as the vendor lists them, with a per-hour column so rows compare. Add-ons such as speaker labels cost extra; see the billing notes.
| Model | Price as listed | Per hour | Notes | Source |
|---|---|---|---|---|
| Whisper Large V3 Turbo | $0.04 per hour | $0.04 | Minimum 10 seconds billed per request. | Sourcechecked 2026-10-25 |
| Whisper (whisper-large-v3) | $0.111 per hour | $0.111 | Minimum 10 seconds billed per request. | Sourcechecked 2026-10-25 |
Write 40, 250 or 5k.
100 hours of audio a month costs from $4.00 (Whisper Large V3 Turbo) to $11.10 (Whisper (whisper-large-v3)).
| Model | Per month | Per hour |
|---|---|---|
| Whisper Large V3 Turbo | $4.00 | $0.04 |
| Whisper (whisper-large-v3) | $11.10 | $0.111 |
List prices in USD on 2026-10-25, before tax, free tiers and add-ons. Rows billed another way are in the price table only.
Groq text to speech prices
Prices as the vendor lists them, with a per-1M-characters column so rows compare.
| Model | Price as listed | Per 1M characters | Notes | Source |
|---|---|---|---|---|
| Canopy Labs Orpheus V1 EnglishPreview | $22.00 per 1M characters | $22.00 | Sourcechecked 2026-10-25 | |
| Canopy Labs Orpheus Arabic SaudiPreview | $40.00 per 1M characters | $40.00 | Sourcechecked 2026-10-25 |
Write 500k, 10M or 1B.
10M characters a month costs from $220.00 (Canopy Labs Orpheus V1 English) to $400.00 (Canopy Labs Orpheus Arabic Saudi).
| Model | Per month | Per 1M characters |
|---|---|---|
| Canopy Labs Orpheus V1 EnglishPreview | $220.00 | $22.00 |
| Canopy Labs Orpheus Arabic SaudiPreview | $400.00 | $40.00 |
List prices in USD on 2026-10-25, before tax, free tiers and add-ons. Rows billed another way are in the price table only.
How the bill is worked out
Batch is half price
Cache discount on a few models
Flex tier costs the same
Audio has a minimum
Groq API pricing questions
How much does the Groq API cost?
Groq bills its language models per million tokens, with separate prices for input, cached input and output. On 2026-10-25, standard prices ran from $0.075 (GPT OSS 20B) to $0.80 (Qwen/Qwen3.8-27B) per 1M input tokens, and $0.30 (GPT OSS 20B) to $4.00 (Qwen/Qwen3.8-27B) per 1M output tokens. Speech to text runs from $0.04 (Whisper Large V3 Turbo) to $0.111 (Whisper (whisper-large-v3)) per hour. Text to speech runs from $22.00 (Canopy Labs Orpheus V1 English) to $40.00 (Canopy Labs Orpheus Arabic Saudi) per 1M characters.
Does Groq offer a batch discount?
Yes. Batch API costs 50% less than the standard price. It suits work that does not need an answer straight away, such as overnight document runs.
How does prompt caching change a Groq bill?
Prompt caching is automatic and free. Cached input tokens get 50% off, but only on GPT-OSS 20B, GPT-OSS 120B and GPT-OSS-Safeguard 20B for now.
Where do these prices come from?
From Groq's own pricing page, https://console.groq.com/docs/models, checked on 2026-10-25. Every row links to it. When a price cannot be confirmed, the row says to check the vendor's page instead of showing a number.
Does Groq discount cached input?
On a few models. Prompt caching is automatic and free, and cached input tokens get 50% off on GPT-OSS 20B, GPT-OSS 120B and GPT-OSS-Safeguard 20B. The batch discount does not stack with the cache discount.
Compare and plan
Building with the Groq API? OceanLab builds AI into business workflows, with people kept in charge. AI automation →
