Can I run Llama 3.1 70B or Skyfall 36B V2 cheaper on another provider?

Some models are available on inference providers like Together AI, Groq, and Fireworks AI at lower prices. Check each model's pricing page for the full provider comparison.

What is the context window difference between Llama 3.1 70B and Skyfall 36B V2?

Llama 3.1 70B has a larger context window at 128K tokens vs 32K. This matters for long documents, large codebases, and extended conversation histories.

Compare

Llama 3.1 70B vs Skyfall 36B V2

Pricing is only the shared seller matrix below. Best rates and catalog map are separate sections, so no chart is embedded in pricing. Open the calculator for the same workload on each side.

MetaLlama 3.1

Model

Llama 3.1 70B

Tool calling

Best $0.400 in · $0.400 out

Context window 128K

Pricing

Thedrummer

Model

Skyfall 36B V2

Best $0.550 in · $0.800 out

Context window 33K

Pricing

Llama 3.1 70B is cheaper across the board — 27% cheaper on input and 50% cheaper on output.

Estimate cost

Pricing matrix

Shared sellers only. Each row is a host that lists both models. Dollar amounts are per 1M tokens. Lowest in each pair of columns is emphasized.

Provider	Llama 3.1 70B in	Llama 3.1 70B out	Skyfall 36B V2 in	Skyfall 36B V2 out
DeepInfra	$0.520	$0.750	N/A	N/A
Fireworks AI	$0.900	$0.900	N/A	N/A
Groq	$0.590	$0.790	N/A	N/A
Openrouter	$0.400	$0.400	$0.550	$0.800
Perplexity	$1.00	$1.00	N/A	N/A
Together AI	$0.880	$0.880	N/A	N/A
Vercel Ai Gateway	$0.720	$0.720	N/A	N/A

Best listed rates (this pair)

Same "best row in current pricing" logic as model pages: a compact view of the lowest input and output we show for each side. This is not the seller matrix.

Catalog map · Meta · Thedrummer

Each chart uses real catalog rows that include both list input and list output ($/1M). Larger green dots are the models on this comparison page; accent dots are other active models from that provider.

Meta · input vs output

Scatter chart: X = input $/M, Y = output $/M. This page's models are labeled on the green dots; hover others for detail.

ListedoutputUSD/1M

One dot per catalog row that has both list prices. Green dots are labeled with the models on this page; hover any dot for name and prices. Upper-right means higher cost on both axes ($/1M).

Thedrummer · input vs output

ListedoutputUSD/1M

One dot per catalog row that has both list prices. Green dots are labeled with the models on this page; hover any dot for name and prices. Upper-right means higher cost on both axes ($/1M).

Specifications

Each column header is the full model name. Tint marks the favorable value where we compute a winner.

Spec

Llama 3.1 70B

Skyfall 36B V2

Context window: 128,000 tokens; 32,768 tokens
Max output tokens: 4,096 tokens; 32,768 tokens
Vision: No; No
Function calling: Yes; No
Streaming: Yes; Yes
Release date: Jul 2024; Mar 2025

Cost calculator

Same requests, input tokens, and output tokens for both columns. Pick the provider row that matches how you buy.

Llama 3.1 70B

Skyfall 36B V2

Requests / day

Input tokens

Output tokens

Llama 3.1 70B

Monthly

$324

Annual

$3.9K

Skyfall 36B V2

Monthly

$285

Annual

$3.5K

Save $39/month with Skyfall 36B V2

When to pick which

Short takeaways: no cards, just the points. Validate with your own workloads.

Long-context tasks
Use Llama 3.1 70B. Its 128K context window handles large codebases and documents better than 32K.
High-volume text generation
Use Llama 3.1 70B. Output tokens are 50% cheaper, which compounds significantly at scale.
Long output (reports, code files)
Use Skyfall 36B V2. Its 32K max output limit reduces the need to split requests.

Frequently asked questions

Llama 3.1 70B is cheaper on both input and output tokens.

More comparisons

Other popular head-to-head matchups.