chooseaimodel
← Compare models

Gemini 3.6 Flash (batch) vs Llama 3.3 70B

List-price comparison ·Gemini 3.6 Flash (batch) details ·Llama 3.3 70B details

ShareXFacebookLinkedIn

For a typical workload (100,000 requests / mo), Llama 3.3 70B is the cheapest — 87% less than the priciest here ($31.60/mo vs $240.00/mo).

 Gemini 3.6 Flash (batch)Llama 3.3 70B
Input / 1M tokens$0.750$0.130
Output / 1M tokens$3.75$0.400
Typical request (1,200 in + 400 out)$0.0024$0.0003
Context window1,048,576 tokens131,072 tokens
Max output65,536 tokens128k tokens
Quality score72/10060/100
TierFlashFlash
ProviderGoogleMeta

Projected monthly cost

Requests / moGemini 3.6 Flash (batch)Llama 3.3 70B
1,000$2.40$0.316
10,000$24.00$3.16
100,000$240.00$31.60
Open all in the calculator — adjust volume and token counts →

Gemini 3.6 Flash (batch)

Auto-synced from OpenRouter — no editorial write-up yet.

Llama 3.3 70B

Mature, well-supported open-weight model for general chat and lightweight agents — wide availability across inference providers keeps pricing competitive.

Falls behind newer flagship models on complex reasoning and coding — best suited to well-scoped, repetitive tasks.

More comparisons

Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.