← Model list
Celeris 1
misc·misc/celeris-1·GA·Closed·NEW
Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.
At a glance
Reference price$2.00 / $6.00 per 1M
Cache read $1.00 · NanoGPT
Lowest paid$2.00 / $6.00
NanoGPT Gateway
Context8,192
Output limit8,192
Capabilities
ReasoningTool useStructured output? TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2026-07-25 / 2026-07-25
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence12.4
Value4
Coding14.4
Agentic2.4
Output speed1596 tok/s
TTFT0.63 s
Cost per task$0.2582
Value formulaIQ 12.4 ÷ min blended $3.000 = 4
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT | Gateway | $2.00 | $6.00 | $1.00 | — | 8,192 | 8,192 |
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
1NanoGPT$580.00
The cheapest paid channel is the only channel.
Related models
Qwen3 Maxcheaper alternative$0.861 / $3.44Qwen3 235B-A22B Instruct 2507cheaper alternative$1.03 / $3.08Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Qwen3-Coder 30B-A3B Instructcheaper alternative$0.216 / $0.861
Price historyone sample accumulated per data sync
Input listOutput listMin blended