These offerings are not all on one meter
This model is metered accelerator instance hour, token. Rates on different meters cannot be read across as cheaper or dearer. The values are still shown, because they are facts; what is withheld is the implication that they are rankable.
Offerings, side by side
Each column is one provider’s commitment to serve this model on its own terms. The reference is a deterministic path into the data — not a recommendation, and not the cheapest.
| Term | Agent MakersFirst Party Managed ApiReference offering | Nimbrex CloudCloud Managed Model | Oryventa ModelsHosted Open Model | Runvora InferenceServerless Inference |
|---|---|---|---|---|
| Channel | First Party Managed Api | Cloud Managed Model | Hosted Open Model | Serverless Inference |
| Status | Deprecated | Deprecated | Active | Active |
| Disclosure | Public List | Public List | Public List | Public List |
| Provider's name for it | Not recorded | Not recorded | Not recorded | Not recorded |
| Processing tiers | Standard, Priority | Standard | Standard, Economy | Standard, Economy |
| Capacity | Shared On Demand | Shared On Demand | Dedicated Compute, Shared On Demand | Shared On Demand |
| Commitment | No commitment option recorded | No commitment option recorded | Term Commitment — the committed amounts are not recorded, only the discount they carry | No commitment option recorded |
| Separately-priced services | Not recorded | Not recorded | Tuning Service | Not recorded |
| Effective from | 1 Jan 2026 | 1 Jan 2026 | 2 May 2025 | 9 May 2025 |
| Captured as of | 31 Aug 2026 | 31 Aug 2026 | 31 Aug 2026 | 31 Aug 2026 |
| Rates recorded | 6 across 2 tiers | 3 across 1 tier | 4 across 2 tiers — 1 tier's cost is not recorded, which is not the same as matching the default | 4 across 2 tiers |
This model’s pricing versions
Every recorded version of every offering’s pricing policy, with its amounts. A scheduled version is a published future price, not a forecast.
- Agent MakersIn forceEffective from 1 Jan 2026 — no end date recordedCaptured as of 31 Aug 2026
- Input tokens $3.40 per 1M tokens
- Output tokens $13.60 per 1M tokens
- Cached input tokens $0.68 per 1M tokens
Input rate down 15.3% on the previous version.
- Agent MakersSupersededEffective from 23 Apr 2025 — 1 Jan 2026Captured as of 1 Jan 2026
- Input tokens $4.012 per 1M tokens
- Output tokens $16.048 per 1M tokens
- Cached input tokens $0.8024 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
- Nimbrex CloudIn forceEffective from 1 Jan 2026 — no end date recordedCaptured as of 31 Aug 2026
- Input tokens $3.128 per 1M tokens
- Output tokens $12.512 per 1M tokens
- Cached input tokens $0.6256 per 1M tokens
Input rate down 15.3% on the previous version.
- Nimbrex CloudSupersededEffective from 9 May 2025 — 1 Jan 2026Captured as of 1 Jan 2026
- Input tokens $3.69104 per 1M tokens
- Output tokens $14.76416 per 1M tokens
- Cached input tokens $0.738208 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
- Oryventa ModelsIn forceEffective from 2 May 2025 — no end date recordedCaptured as of 31 Aug 2026
- Input tokens $2.312 per 1M tokens
- Output tokens $9.248 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
- Runvora InferenceIn forceEffective from 9 May 2025 — no end date recordedCaptured as of 31 Aug 2026
- Input tokens $2.652 per 1M tokens
- Output tokens $10.608 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.