Cheaper Inference
Model record / Sao10K
l3-8b-stheno-v3.2 is available for text generation from Sao10K. Its reported context window is 8,192 tokens, with up to 32,000 output tokens. Observed input: text (verified request). The served catalog lists streaming.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/chat/completions
curl https://api.cheaperinference.com/v1/chat/completions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "l3-8b-stheno-v3.2", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ] }'$0.0715 estimated at displayed rates
1,000,000 ÷ 1,000,000 × $0.0572 + 250,000 ÷ 1,000,000 × $0.0572
Uses uncached input at the displayed standard rates, with no extra modalities or tools. Billed output includes any charged reasoning tokens. Actual token counts, price tiers, and marketplace prices can change the total.
Price quote effective .
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| l3-8b-stheno-v3.2 (this model)Sao10K | $0.0572 input / $0.0572 output per 1M tokens | 8,192 tokens | No |
| deepseek-v3DeepSeek | $0.2295 input / $0.935 output per 1M tokens | 64,000 tokens | No |
| deepseek-v3.1DeepSeek | $0.1625 input / $0.6175 output per 1M tokens | 128,000 tokens | No |
| deepseek-v3.2-thinking |
This model takes the fields in its sample request. It has no other stated parameters.
See how much this model saves and when its recorded price has been lowest.
This model averaged 0.0% below comparable direct provider prices across the selected range. Its strongest observed window was 12:00 PM–10:00 AM in UTC.
Average saved
0.0%
Cheapest time
12:00 PM–10:00 AM
Hourly coverage
23/24
Signal quality
Growing
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#302
of 332 ranked models
Last 7 days
#338
of 389 ranked models
Last 30 days
#345
of 400 ranked models
| $0.182 input / $0.273 output per 1M tokens |
| 128,000 tokens |
| No |