← Model list
L3 8B Stheno V3.2
meta·meta/l3-8b-stheno-v3.2-2·GA·Open weights·llama series
Open Llama instruction model for multilingual chat, reasoning, and coding
At a glance
Reference price$0.05 / $0.05 per 1M
Cache read — · NovitaAI
Lowest paid$0.05 / $0.05
NovitaAI Gateway
Context8,192
Output limit32,000
Capabilities
Reasoning✓ Tool use? Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2024-11-29 / 2024-11-29
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NovitaAI sao10K/L3-8B-stheno-v3.2 | Gateway | $0.05 | $0.05 | — | — | 8,192 | 32,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NovitaAI$12.50
The cheapest paid channel is the only channel.
Related models
Llama 3.3 70Bsame series$1.75 / $2.75Llama Guard 4 12Bsame series$0.18 / $0.18Llama 4 Mavericksame series$0.20 / $0.80text-embedding-3-smallcheaper alternative$0.02 / $0Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Lyria 3 Clip Previewcheaper alternative$0 / $0MiMo-V2.5-TTS-VoiceDesigncheaper alternative$0 / $0
Price historyone sample accumulated per data sync
Input listOutput listMin blended