Identity
- Model
- Ctxdex Chikitsa 2
- Provider
- Oryventa Models
- Channel
- Hosted Open Model
- Provider's name for it
- Not recorded
- Offering
- ctxdex:offering:oryventa-models:ctxdex-chikitsa-2
- Currency
- USD
Rates
Charged by Oryventa Models on this offering. Effective from 9 Jun 2026. Captured as of 31 Aug 2026.
Applies unless another rate set's condition is met.
| Meter | Rate | As recorded |
|---|---|---|
| Input tokens | $1.904per 1M tokens | 1.904 USD / 1000000 TOKEN |
| Output tokens | $4.08per 1M tokens | 4.08 USD / 1000000 TOKEN |
Where this sits in the industry
The external offerings this one is compared against, captured as of 2026-09-14. Each names the surface it is sold on and how well that surface matches this one. No price is shown here: most of these providers do not publish one per unit, and the link goes to whatever they do publish.
Google Vertex AI / Model Garden — MedGemma 1.5 4B
Sold as Model Garden, managed or model distribution.
Uses Google Vertex AI / Model Garden — MedGemma 1.5 4B as the ranked 1 current commercial/access reference. Surface fit to CTXDEX role HOSTED_OPEN_MODEL: DIRECT.
This provider publishes or documents its pricing. This provider publishes no per-unit rate, so there is nothing to compare a cost against.
Provider pricing pageGoogle Vertex AI / Model Garden — MedGemma 27B
Sold as Model Garden, managed or model distribution.
Uses Google Vertex AI / Model Garden — MedGemma 27B as the ranked 2 current commercial/access reference. Surface fit to CTXDEX role HOSTED_OPEN_MODEL: DIRECT.
This provider publishes or documents its pricing. This provider publishes no per-unit rate, so there is nothing to compare a cost against.
Provider pricing pageOpenAI API — GPT-Rosalind
OpenAI
Sold as Native API, public self service.
Surface differs: CTXDEX commercial role is HOSTED_OPEN_MODEL; external reference surface is NATIVE_API / PUBLIC_SELF_SERVICE.
Uses OpenAI API — GPT-Rosalind as the ranked 3 current commercial/access reference. Surface fit to CTXDEX role HOSTED_OPEN_MODEL: REFERENCE.
This provider publishes or documents its pricing. This provider publishes no per-unit rate, so there is nothing to compare a cost against.
Provider pricing pageConditions & rules
A headline rate is not what you pay. Everything below changes it, and none of it is reflected in the figures above.
- Effective from
- 9 Jun 2026
- Effective to
- No end date recorded
- Captured as of
- 31 Aug 2026
- Eligibility
- Published list pricing — available to anyone on this channel.
- Offering status
- Active
- Capacity
- Dedicated Compute, Shared On Demand. Capacity beyond shared on-demand is priced on its own basis, shown as its own rate set where one is recorded.
- Commitment
- Term Commitment. The committed amounts are not recorded — a commitment appears here as the discount it carries, not as a price.
- Tier coverage
- 2 tiers recorded, and 1 of them — Economy — carry no recorded cost. That is not the same as matching the default rate.
- Separately-priced services
- Tuning Service. These are charged in addition to the rates above.
Pricing rules
A pricing rule is a recorded Commitment — open the definition that changes what a Rate Schedule — open the definition charges — an Allowance — open the definition, a band, a premium or a Spend Commitment — open the definition.
- commitment discount
Eligible charges are 18% less under a recorded commitment.
Pricing versions
Every recorded version of this offering's pricing policy, newest first, with its amounts. A scheduled version is a published future price, not a forecast.
- Oryventa ModelsIn forceEffective from 9 Jun 2026 — no end date recordedCaptured as of 31 Aug 2026
- Input tokens $1.904 per 1M tokens
- Output tokens $4.08 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.