Gemini API vs Groq: LLM API pricing compared
Updated 2026-11-09 · listed A to Z, not ranked
Google prices the Gemini API per million tokens on its Standard paid tier, with a free tier on some models. Two models list a price change on a set date, so check which date applies to you.
Groq runs its own LPU inference hardware and sells model access through GroqCloud, an OpenAI-compatible API billed per token (language models), per hour of audio (Whisper) or per character (text to speech).
Listed A to Z, from ai.google.dev and console.groq.com. Every figure below is quoted from those pages.
- Main price table
- Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite, Gemini 3.1 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini Embedding
- Free option
- None in the published plan table
- Published prices
- Gemini 4 Argon, 3.8 Flash, 3.5 Flash-Lite, 3.1 Pro Preview and 2.5 models, scheduled price changes, batch and grounding.
- Main price table
- GPT OSS 120B (openai/gpt-oss-120b), GPT OSS 20B (openai/gpt-oss-20b), Llama 3.1 8B Instant, Llama 3.3 70B Versatile, Whisper Large V3, Whisper Large V3 Turbo
- Free option
- None in the published plan table
- Published prices
- GPT OSS 120B $0.15 in / $0.60 out per 1M tokens, GPT OSS 20B $0.075 / $0.30, Whisper Large V3 Turbo $0.04 per hour.
How we checked: Prices quoted from each official pricing page: Gemini API checked Nov 9, 2026, Groq checked Nov 9, 2026. Taxes, usage overages and promotions can change what you pay; confirm with each provider before you buy.
How they compare
- Main price table. Gemini API lists 8 entries (Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite, Gemini 3.1 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini Embedding); Groq lists 6 (GPT OSS 120B (openai/gpt-oss-120b), GPT OSS 20B (openai/gpt-oss-20b), Llama 3.1 8B Instant, Llama 3.3 70B Versatile, Whisper Large V3, Whisper Large V3 Turbo).
- Free option. Gemini API: none in the published plan table. Groq: none in the published plan table.
- How prices are quoted. Gemini API: “Standard paid tier (per 1M tokens)”. Groq: “Production models”.
Gemini API plans and prices
| Model | Input | Output | Free tier |
|---|---|---|---|
| Gemini 4 Argon | $2.00 through Nov 30, 2026; $4.00 from Dec 1, 2026 | $10.00; then $20.00 | No |
| Gemini 3.8 Flash | $0.75 through Dec 31, 2026; $1.50 from Jan 1, 2027 | $3.75; then $7.50 | Yes |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | Yes |
| Gemini 3.1 Flash-Lite | $0.25 text/image/video ($0.50 audio) | $1.50 | |
| Gemini 3.1 Pro Preview | $2 (prompts up to 200K) / $4 (over 200K) | $12 / $18 | No |
| Gemini 2.5 Pro | $1.25 / $2.50 (over 200K) | $10 / $15 | |
| Gemini 2.5 Flash | $0.30 | $2.50 | |
| Gemini Embedding | $0.15 |
| Item | Price |
|---|---|
| Batch and Flex | 50% of Standard (Argon batch $1 / $5) |
| Priority (Gemini 4 Argon) | $3.60 input / $18 output |
| Grounding with Google Search | 5,000 prompts a month free (shared), then $14 per 1,000 |
From ai.google.dev, checked Nov 9, 2026. Full breakdown: Gemini API pricing.
Groq plans and prices
| Model | Speed (tokens/sec) | Price | Context window |
|---|---|---|---|
| GPT OSS 120B (openai/gpt-oss-120b) | ~500 | $0.15 input / $0.60 output per 1M tokens | 131,072 |
| GPT OSS 20B (openai/gpt-oss-20b) | ~1,000 | $0.075 input / $0.30 output per 1M tokens | 131,072 |
| Llama 3.1 8B Instant | ~560 | Enterprise: contact sales | 131,072 |
| Llama 3.3 70B Versatile | ~280 | Enterprise: contact sales | 131,072 |
| Whisper Large V3 | — | $0.111 per hour of audio | — |
| Whisper Large V3 Turbo | — | $0.04 per hour of audio | — |
Developer plan rate limits on the same page: GPT OSS 120B 250K tokens/min and 1K requests/min; Whisper Large V3 Turbo 400K audio seconds/hour.
| Model | Price |
|---|---|
| Qwen3.8 27B | $0.80 input / $4.00 output per 1M tokens |
| Safety GPT OSS 20B | $0.075 input / $0.30 output per 1M tokens |
| Canopy Labs Orpheus V1 English (TTS) | $22.00 per 1M characters |
| Canopy Labs Orpheus Arabic Saudi (TTS) | $40.00 per 1M characters |
| Llama Prompt Guard 2 22M / 86M | $0.03 / $0.04 per 1M tokens (input and output) |
Groq says preview models may be discontinued at short notice and should not be used in production.
From console.groq.com, checked Nov 9, 2026. Full breakdown: Groq pricing.
FAQ
How much does Gemini API cost?
Gemini 4 Argon, 3.8 Flash, 3.5 Flash-Lite, 3.1 Pro Preview and 2.5 models, scheduled price changes, batch and grounding. (checked Nov 9, 2026).
How much does Groq cost?
GPT OSS 120B $0.15 in / $0.60 out per 1M tokens, GPT OSS 20B $0.075 / $0.30, Whisper Large V3 Turbo $0.04 per hour. (checked Nov 9, 2026).
Do Gemini API and Groq have a free option?
Gemini API: none in the published plan table. Groq: none in the published plan table.
Where do these prices come from?
Each vendor's own pricing page: ai.google.dev (checked Nov 9, 2026) and console.groq.com (checked Nov 9, 2026). Prices change; confirm on the vendor's page before you buy.
Sources (official pages, read 2026-11-09)
- ai.google.dev
- ai.google.dev/gemini-api/docs/pricing
- console.groq.com
- console.groq.com/docs/models
- groq.com/pricing
Spot something out of date? Email hello@youraitools.co and we’ll fix it.