Celeris-1
AI model by Celeris. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Celeris-1 is a budget-tier option from Celeris at $0.70/M output tokens. Despite the low price, it scores competitively on Coding Index (14.4) and Intelligence Index (12.4) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Celeris-1 reports 1621 tok/s output speed and 630ms 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 $0.27 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Celeris-1Current | $0.20 | $0.70 | 1621 tok/s |
| Hermes 3 - Llama-3.1 70B | $0.70 | $0.70 | 35 tok/s |
| Qwen3 VL 8B Instruct | $0.18 | $0.70 | 112 tok/s |
| Mixtral 8x7B Instruct | $0.45 | $0.70 | — |
| Qwen3 8B (Non-reasoning) | $0.18 | $0.70 | 41 tok/s |
| Llama 3.3 Instruct 70B | $0.66 | $0.72 | 85 tok/s |