R1 Distill Llama 70B vs Lyria 3 Clip Preview vs GLM 4.5
R1 Distill Llama 70B at $0.920 in and $0.920 out, Lyria 3 Clip Preview at $0 in and $0 out, and GLM 4.5 at $0.690 in and $2.53 out — per million tokens, from the same wallet.
R1 Distill Llama 70B
DeepSeek
0.53¢
for a client proposal
$0.920 in · $0.920 out / 1M
8K context · released January 2025
Lyria 3 Clip Preview
Free
for a client proposal
$0 in · $0 out / 1M
1.05M context · released 4 months ago
GLM 4.5
Z.ai
0.55¢
for a client proposal
$0.690 in · $2.53 out / 1M
131K context · released July 2025
Asking all three at once — identical prompt, identical context — costs about 1.1¢ for a typical client proposal.
At a glance
- Cheapest input: Lyria 3 Clip Preview at $0 per million tokens.
- Cheapest output: Lyria 3 Clip Preview at $0 per million tokens.
- Largest context: Lyria 3 Clip Preview at 1.05M tokens — about 1,500 pages.
Cost per task
Estimated totals at the rates above. Solid bar is input, lighter bar is output.
Quick code fix
2K in · 500 outDraft a client proposal from notes
5K in · 800 outContext-heavy session (Alyph workspace)
155K in · 4K outAnalyze a 50-page legal contract
35K in · 1K outLarge architecture refactor
250K in · 3K outSolid part of each bar is input tokens, the lighter part is output. Models that don’t fit a task are marked instead of priced.
Cost vs Token Amount
Drag the slider to adjust the split between input and output workload.
Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.
Pricing
Specs
Try it with real numbers
2K tokens in · 500 tokens out.
All 3, same prompt and context: 0.49¢. That is the entire cost of the comparison.
Your $5 welcome credit covers about 1,011 of these.
Which should you pick?
For long documents, Lyria 3 Clip Preview has the largest context window here — 1.05M tokens.
On price, Lyria 3 Clip Preview is the cheapest of the three on a typical task, at about free.
For images or files, Lyria 3 Clip Preview can read them directly; R1 Distill Llama 70B and GLM 4.5 are text-only.
If you want to watch the model think, R1 Distill Llama 70B and GLM 4.5 show reasoning; the other answers directly.
Or don’t pick. Send the identical prompt to all three, read the answers side by side, and keep the winner. How to run a fair bake-off →
Questions, answered
Which is cheapest — R1 Distill Llama 70B, Lyria 3 Clip Preview, or GLM 4.5?
Which has the largest context window?
Can I run R1 Distill Llama 70B, Lyria 3 Clip Preview, and GLM 4.5 side by side on Alyph?
Ask all three at once
Identical prompt, identical context, answers side by side — about 1.1¢ for a typical client proposal. Free to start, with $5 of credit.