Ctxdex Foundation 3 Instruct pricing

These offerings are not all on one meter

This model is metered accelerator instance hour, throughput unit 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.

Ctxdex Foundation 3 Instruct — every current commercial offering, with terms aligned across columns.
Term	Agent MakersFirst Party Managed ApiReference offering	Astavra Enterprise AIEnterprise Managed Ai	Nimbrex CloudCloud Managed Model	Oryventa ModelsHosted Open Model	Runvora InferenceServerless Inference
Channel	First Party Managed Api	Enterprise Managed Ai	Cloud Managed Model	Hosted Open Model	Serverless Inference
Status	Active	Active	Active	Active	Active
Disclosure	Public List	Public List	Public List	Public List	Public List
Provider's name for it	Not recorded	Not recorded	Not recorded	Not recorded	Not recorded
Processing tiers	Standard, Priority	Standard, Priority	Standard, Priority	Standard, Economy	Standard, Economy
Capacity	Shared On Demand	Dedicated Compute, Provisioned Throughput	Provisioned Throughput, Shared On Demand	Dedicated Compute, Shared On Demand	Shared On Demand
Commitment	No commitment option recorded	Enterprise Contract, Term Commitment — the committed amounts are not recorded, only the discount they carry	Term Commitment — the committed amounts are not recorded, only the discount they carry	Term Commitment — the committed amounts are not recorded, only the discount they carry	No commitment option recorded
Separately-priced services	Search Grounding, Web Search	Map Grounding	File Search, Web Fetch	Tuning Service	Code Execution, Remote Tool Access
Effective from	15 Sep 2026	15 Sep 2026	15 Sep 2026	15 Sep 2026	15 Sep 2026
Captured as of	14 Sep 2026	14 Sep 2026	14 Sep 2026	14 Sep 2026	14 Sep 2026
Rates recorded	6 across 2 tiers — 1 tier's cost is not recorded, which is not the same as matching the default	4 across 2 tiers — 1 tier's cost is not recorded, which is not the same as matching the default	4 across 2 tiers — 1 tier's cost is not recorded, which is not the same as matching the default	4 across 2 tiers — 1 tier's cost is not recorded, which is not the same as matching the default	6 across 2 tiers

Who else sells something like this

11 external offerings from 7 providers, captured as of 2026-09-14. Each offering’s own page names the surface every one is sold on and links to the provider’s pricing. No price is shown on either: most of these providers do not publish one per unit.

Fireworks AI · 3 offeringsAmazon Bedrock · 2 offeringsMicrosoft Foundry / Fireworks · 2 offeringsAlibaba Cloud · 1 offeringGoogle · 1 offeringMicrosoft Foundry · 1 offeringMistral AI · 1 offering

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 15 Sep 2026 — no end date recordedCaptured as of 14 Sep 2026
- Audited base input-token rate $0.38 per 1M tokens
- Audited base output-token rate $1.55 per 1M tokens
- Audited base cached-input-token rate $0.038 per 1M tokens
Input rate down 78.9% on the previous version.
Agent MakersSupersededEffective from 1 Apr 2026 — 15 Sep 2026Captured as of 31 Aug 2026
- Input tokens $1.80 per 1M tokens
- Output tokens $7.20 per 1M tokens
- Cached input tokens $0.36 per 1M tokens
Input rate down 15.3% on the previous version.
Agent MakersSupersededEffective from 13 Feb 2026 — 1 Apr 2026Captured as of 1 Apr 2026
- Input tokens $2.124 per 1M tokens
- Output tokens $8.496 per 1M tokens
- Cached input tokens $0.4248 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
Astavra Enterprise AIIn forceEffective from 15 Sep 2026 — no end date recordedCaptured as of 14 Sep 2026
- Audited base input-token rate $0.50 per 1M tokens
- Audited base output-token rate $1.90 per 1M tokens
- Audited base cached-input-token rate $0.075 per 1M tokens
Input rate down 79.4% on the previous version.
Astavra Enterprise AISupersededEffective from 16 Mar 2026 — 15 Sep 2026Captured as of 31 Aug 2026
- Input tokens $2.43 per 1M tokens
- Output tokens $9.72 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
Nimbrex CloudIn forceEffective from 15 Sep 2026 — no end date recordedCaptured as of 14 Sep 2026
- Audited base input-token rate $0.43 per 1M tokens
- Audited base output-token rate $1.75 per 1M tokens
- Audited base cached-input-token rate $0.043 per 1M tokens
Input rate down 74.0% on the previous version.
Nimbrex CloudSupersededEffective from 1 Apr 2026 — 15 Sep 2026Captured as of 31 Aug 2026
- Input tokens $1.656 per 1M tokens
- Output tokens $6.624 per 1M tokens
- Cached input tokens $0.3312 per 1M tokens
Input rate down 15.3% on the previous version.
Nimbrex CloudSupersededEffective from 2 Mar 2026 — 1 Apr 2026Captured as of 1 Apr 2026
- Input tokens $1.95408 per 1M tokens
- Output tokens $7.81632 per 1M tokens
- Cached input tokens $0.390816 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
Oryventa ModelsIn forceEffective from 15 Sep 2026 — no end date recordedCaptured as of 14 Sep 2026
- Audited base input-token rate $0.31 per 1M tokens
- Audited base output-token rate $1.18 per 1M tokens
- Audited base cached-input-token rate $0.031 per 1M tokens
Input rate down 74.7% on the previous version.
Oryventa ModelsSupersededEffective from 17 Feb 2026 — 15 Sep 2026Captured as of 31 Aug 2026
- Input tokens $1.224 per 1M tokens
- Output tokens $4.896 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.
Runvora InferenceIn forceEffective from 15 Sep 2026 — no end date recordedCaptured as of 14 Sep 2026
- Audited base input-token rate $0.28 per 1M tokens
- Audited base output-token rate $1.05 per 1M tokens
- Audited base cached-input-token rate $0.028 per 1M tokens
Input rate down 80.1% on the previous version.
Runvora InferenceSupersededEffective from 1 Apr 2026 — 15 Sep 2026Captured as of 31 Aug 2026
- Input tokens $1.404 per 1M tokens
- Output tokens $5.616 per 1M tokens
Input rate down 15.3% on the previous version.
Runvora InferenceSupersededEffective from 21 Feb 2026 — 1 Apr 2026Captured as of 1 Apr 2026
- Input tokens $1.65672 per 1M tokens
- Output tokens $6.62688 per 1M tokens
The earliest recorded version, so there is nothing before it to compare with.