Celeris
Celeris-1
Closed weights
- Intelligence
- 6.3
- Rank 634 of 762 measured models
- Coding
- 14.4
- Rank 249 of 299 measured models
- Output speed
- 1,663 t/s
- Rank 1 of 420 measured models
- Price/1M
- $0.325
- Rank 240 of 716 measured models
- Context window
- 1M
- Rank 88 of 1283 measured models
- Cost per task
- $0.0502
- Rank 31 of 214 measured models
Celeris-1 scores 6.3 on the Artificial Analysis Intelligence Index, ranking 634th of 762 measured models. The closest models on this index are EXAONE 4.0 32B (6.3), Grok-1 (6.3), and Muse Glimmer (High) (6.3). At $0.325 per million tokens (3:1 input/output blended price), it is cheaper than Muse Glimmer (High) ($0.525). With an output speed of 1,663 t/s, it is faster than Muse Glimmer (High) (104 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- EXAONE 4.0 32B
LG AI Research · — · —
6.3——Compare - Grok-1
SpaceXSI · — · —
6.3——Compare - Muse Glimmer (High)
Meta · $0.525 · 104 t/s
6.3$0.525104 t/sCompare - Phi-4 Mini Instruct
Microsoft · $0.131 · 45.6 t/s
6.3$0.13145.6 t/sCompare
