Celeris-1
AI model by Celeris. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Celeris-1 is positioned in the mid-tier at $6.00/M output tokens. The benchmark profile is balanced — strongest on GPQA Diamond (63.1%) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Celeris-1 reports 2146 tok/s output speed and 469ms time-to-first-token. Output speed is in the top tier — usable for streamed interactive UIs.
Cost model. For a workload of 1M input tokens + 100K output tokens, Celeris-1 costs $2.60 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-04.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Celeris-1Current | $2.00 | $6.00 | 2146 tok/s |
| Grok 4.5 (high) | $2.00 | $6.00 | 59 tok/s |
| Qwen3 Next 80B A3B (Reasoning) | $0.50 | $6.00 | 206 tok/s |
| Qwen3.8 Max | $2.00 | $6.00 | 51 tok/s |
| Mistral Large 2 (Jul '24) | $2.00 | $6.00 | 0 tok/s |
| Grok 4.20 0309 (Reasoning) | $2.00 | $6.00 | 0 tok/s |