LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
mi

Celeris 1

misc·misc/celeris-1·GA·Closed
Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$2.00 / $6.00
Blended $3.00
Context
8,192
Output limit
8,192
Knowledge cutoff
—
Released / updated
2026-07-25 / 2026-07-25
Capabilities
ReasoningTool useStructured output? TemperatureAttachments
Modalities
Text

Celeris 1 by misc is currently listed from a single provider. No official API price is listed for it; the prices below come from third-party channels.

Median output speed is 1543 tokens per second, with 0.55s to the first token.

The context window is 8,192 tokens, with an output limit of 8,192 tokens.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed1543 tok/s
TTFT0.55 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers1 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    $2.00 / $6.00
    Cache read $1.00Context 8,192Output limit 8,192
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$2.00$6.00$1.00—8,1928,192

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

Common scenarios
1NanoGPT$580.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $3.00

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations13 items

GPQA Diamond63.1%
Humanity's Last Exam6.8%
HLE-Diamond5.7%
CritPt0.0%
SciCode21.6%
Terminal-Bench 2.111.2%
Terminal-Bench 4.00.0%
τ³-Bench Banking3.9%
AutomationBench-AA0.4%
AA-Briefcase152
GDPval-AA309
GDP.pdf1.2%
AA-LCR38.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

miBee Swarm 1.0same lab—miCicerosame lab—
Data partly from models.dev (MIT)