Ctxdex Open General 3

Overview

Intended useBest suited for complex reasoning, code generation, general language generation, multimodal understanding, and tool-enabled workflows.

FamilyCtxdex Open GeneralHybrid open/commercial general-intelligence family with occasional specialist variants.

AnnouncedAnnounced2025-01-14

DeprecatedDeprecated2025-10-28

RetiredNot applicableModel is not retired.

What it does

Capabilities carry their support status; tasks are labels, because seven descriptions would bury the section.

Capabilities (3)

Explicit Reasoning · Partial support: Intrinsic explicit/deliberate reasoning support.
Structured Output: Intrinsic support for constrained/structured machine-readable output.
Tool Calling: Intrinsic support for requesting/invoking external tools/functions.

Tasks (4)

Code GenerationComplex ReasoningGeneral Language GenerationMultimodal Understanding

Inputs & Outputs

Each modality is paired with the representation it is carried in, so a non-token model reads the same way a text one does.

Accepts

ImageRaster Image
TextChat Messages

Produces

TextPlain Text

Technical Characteristics

A characteristic with no value states why it has none. An absence here is a recorded fact, not a gap in the page.

Knowledge/training cutoff2024-03-01

Maximum context tokens64000

Maximum native output tokens8000

Architecture classDENSE_TRANSFORMER

Parameter count24.000000000000000000

Versions & Snapshots

Latest2025-01-28

Opening a snapshot shows what it resolves to. It does not switch this page into snapshot mode — the model's own values stay in place.

Snapshot	Released	Status	Detail
2025-01-28	2025-01-28	Active snapshot

Availability

Current offering available

Agent Makers

First Party Managed Api

Deprecated offering

Effective from2025-02-09

Serving surfaces

Inference API · Deprecated

Nimbrex Cloud

Cloud Managed Model

Deprecated offering

Effective from2025-03-02

Serving surfaces

Inference API · Deprecated

Oryventa Models

Hosted Open Model

Active offering

Effective from2025-02-09

Serving surfaces

Inference API · Active

Runvora Inference

Serverless Inference

Active offering

Effective from2025-02-27

Serving surfaces

Inference API · Active

Historical offeringsNone recorded

Downloadable distributions1

Distributions

A downloadable artefact under this model's licence. Format, precision and size are properties of the artefact, not of the model.

Optimized Package

Deprecated distribution

ONNXINT8INT825.4 GB

Available from2025-03-04

Serving Performance

Measured as of2026-09-07

Every figure is measured under the conditions beside it. Read without them, a latency number claims more than it can.

Measurement basis Synthetic ProfileMetrics 8

Metric	Typical value	Conditions
Output Tokens Per SecondSteady generated text-token rate after first token.	81.6Token Per Second	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGProcessing Tier: STANDARDConcurrency Band: C1Output Size Band: ~512_TOKENS
Output Tokens Per SecondSteady generated text-token rate after first token.	79.4Token Per Second	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGProcessing Tier: STANDARDConcurrency Band: C1Output Size Band: ~512_TOKENS
Output Tokens Per SecondSteady generated text-token rate after first token.	86.4Token Per Second	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGProcessing Tier: STANDARDConcurrency Band: C1Output Size Band: ~512_TOKENS
Output Tokens Per SecondSteady generated text-token rate after first token.	72.5Token Per Second	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGProcessing Tier: STANDARDConcurrency Band: C1Output Size Band: ~512_TOKENS
Time To First Token MsLatency from accepted request/start of generation to first generated text token.	320Ms	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGInput Size Band: ~4K_TOKENSProcessing Tier: STANDARDConcurrency Band: C1
Time To First Token MsLatency from accepted request/start of generation to first generated text token.	260Ms	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGInput Size Band: ~4K_TOKENSProcessing Tier: STANDARDConcurrency Band: C1
Time To First Token MsLatency from accepted request/start of generation to first generated text token.	285Ms	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGInput Size Band: ~4K_TOKENSProcessing Tier: STANDARDConcurrency Band: C1
Time To First Token MsLatency from accepted request/start of generation to first generated text token.	285Ms	Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGInput Size Band: ~4K_TOKENSProcessing Tier: STANDARDConcurrency Band: C1

Pricing Reference

Reference offering

Agent Makers · First Party Managed Api

Effective from2026-01-01Captured as of2026-08-31

Meter	Basis	Rate
Input	Input tokens	$1.8 / 1000000Token
Output	Output tokens	$7.2 / 1000000Token
Cached Input	Cached input tokens	$0.36 / 1000000Token

View all pricing

Full pricing for a single offering is one step further in, from this model’s pricing page, because it is addressed by offering and this page carries the model. The calculator is disabled because it is not built.

These rates are still recorded and still effective-dated, on a deprecated offering. They are not withdrawn, and they are not a current recommendation. 3 other current offerings are priced separately. This is the publisher's own offering, chosen as the reference — it is not the cheapest by definition. Rates are not comparable across offerings unless meter, unit and conditions match.

Derived chronology

Model Journey

Assembled from this model’s own lifecycle records, its snapshots, its providers’ offering and pricing history, and recorded succession. It is a view over those records, not a second source of truth, and undated lineage is deliberately not on it.

19 events

Effective from 2026-01-27
SuccessionMajor
Recommended successor: Ctxdex Open General 4
Effective from 2026-01-01
PricingNormal
Agent Makers pricing became effective
Offering context: Agent Makers
Version current, effective from 2026-01-01.
Effective from 2026-01-01
PricingNormal
Nimbrex Cloud pricing became effective
Offering context: Nimbrex Cloud
Version current, effective from 2026-01-01.
Effective from 2026-01-01
PricingNormal
Runvora Inference pricing became effective
Offering context: Runvora Inference
Version current, effective from 2026-01-01.
Effective from 2025-10-28
ModelMajor
Model status changed to Deprecated
Effective from 2025-10-28
AvailabilityNormal
Agent Makers · First Party Managed Api: Deprecated
Offering context: Agent Makers
Synthetic provider deprecation.

Open full journey →

The first control expands this section in place, without filters or navigation. The second opens the standalone journey, which adds filtering on three axes, year grouping, per-event provenance and a shareable address.

Every date is the source record’s own effective date — a model lifecycle date, a snapshot release, an offering’s effective date, a pricing version’s effective-from. None of them is a load or capture timestamp.

Licence & Use Conditions

LicenceAgent Makers Open Weight License

Version1.0

SPDX identifierNot applicableNo SPDX identifier is recorded for these terms.

Legal textNo public URI recordedThe terms exist and are held internally; no public address has been published.Captured as of2026-09-07

Use conditions (0)

None recordedNo condition constrains use of this model beyond its licence.

Lifecycle & Lineage

Direct lineage

Derived From of

Ctxdex Open General 3 Code

Successor Of

Ctxdex Open General 2

Successor Of of

Ctxdex Open General 4

Replaced by

Ctxdex Open General 4

Effective from2026-01-27

Lifecycle history: Active on 2025-01-28, then Deprecated on 2025-10-28.

Similar Industry Models, as last compared

Captured as of2026-09-07

A positioning reference drawn while this model was current, and not maintained since — superseded on 2026-09-14. Each row states the axes it was drawn on.

Mistral Large 3

Mistral AI

Provider documentation

Frontier General PurposeMultimodalOpen Deployability

Broadly comparable on general-purpose language work and multimodal understanding. It also provides a current open/deployable reference point; licence terms are not assumed to match. This row covers only part of the ctxdex model's capability positioning.

Gemma 4 12B

Google DeepMind

Provider documentation

Frontier General PurposeReasoningMultimodalCodingOpen Deployability

Broadly comparable on general-purpose language work, complex reasoning, multimodal understanding, and coding. It also provides a current open/deployable reference point; licence terms are not assumed to match.

Comparison method ctxdex-industry-comparable-method-v1.