LLM Cost Calculator

GPT-OSS 120B (Groq) vs DeepSeek V4 Pro — LLM API Cost Comparison

Compare GPT-OSS 120B (Groq) (Groq) vs DeepSeek V4 Pro (DeepSeek) on cost per million tokens, context window, and monthly spend.

Prices verified 2026-05-23 · Pricing may change — use the calculator for current estimates

Groq
GPT-OSS 120B (Groq)
Current
Input
$0.15/1M tokens
Output
$0.6/1M tokens
Context
128K tokens
Released
2025-12

OpenAI open-source model on Groq; 500 tokens/sec

DeepSeek
DeepSeek V4 Pro
Current
Input
$1.74/1M tokens
Output
$3.48/1M tokens
Context
1M tokens
Released
2026-03

DeepSeek flagship; 1M context; promo 75% off ($0.435/$0.87) until May 31 2026

Monthly Cost by Usage Tier (70% input / 30% output ratio)

UsageGPT-OSS 120B (Groq)DeepSeek V4 ProCheaper by
Light (1M tokens)$0.285$2.26GPT-OSS 120B (Groq) (87%)
Moderate (10M tokens)$2.85$22.62GPT-OSS 120B (Groq) (87%)
Heavy (100M tokens)$28.50$226GPT-OSS 120B (Groq) (87%)
Very Heavy (1B tokens)$285$2,262GPT-OSS 120B (Groq) (87%)

Frequently Asked Questions

Which is cheaper — GPT-OSS 120B (Groq) or DeepSeek V4 Pro?

For input tokens, GPT-OSS 120B (Groq) is cheaper at $0.15/1M tokens — 11.6× less than $1.74/1M. For output tokens, GPT-OSS 120B (Groq) wins at $0.6/1M vs $3.48/1M. At heavy workloads (100M tokens/month), the cost difference can be significant.

What is the context window difference between GPT-OSS 120B (Groq) and DeepSeek V4 Pro?

GPT-OSS 120B (Groq) supports 128,000 tokens per request; DeepSeek V4 Pro supports 1,000,000 tokens. DeepSeek V4 Pro wins on context length, making it better for long documents, large codebases, or extended conversations without chunking.

When should I choose GPT-OSS 120B (Groq) over DeepSeek V4 Pro?

Choose GPT-OSS 120B (Groq) (Groq) if you prefer Groq's ecosystem, tooling, or reliability track record. OpenAI open-source model on Groq; 500 tokens/sec. Choose DeepSeek V4 Pro (DeepSeek) if DeepSeek flagship; 1M context; promo 75% off ($0.435/$0.87) until May 31 2026. the price/performance fits your workload better. Use this calculator to find the break-even point for your exact token volume.

How much does 1 billion tokens cost on GPT-OSS 120B (Groq) vs DeepSeek V4 Pro?

At 700M input + 300M output tokens (1B total): GPT-OSS 120B (Groq) costs $285; DeepSeek V4 Pro costs $2262. The difference is $1977/billion tokens at this 70/30 input/output ratio.