Overview
Intended useBest suited for code generation, general language generation, multimodal understanding, and tool-enabled workflows. |
FamilyCtxdex Open GeneralHybrid open/commercial general-intelligence family with occasional specialist variants. |
AnnouncedAnnounced |
DeprecatedNot applicableModel is current. |
RetiredNot applicableModel is not retired. |
What it does
Capabilities carry their support status; tasks are labels, because seven descriptions would bury the section.
Capabilities (2)
- Structured Output
- Intrinsic support for constrained/structured machine-readable output.
- Tool Calling
- Intrinsic support for requesting/invoking external tools/functions.
Tasks (3)
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.
Availability
Current offering availableAgent Makers
First Party Managed Api
Serving surfaces
Nimbrex Cloud
Cloud Managed Model
Serving surfaces
Oryventa Models
Hosted Open Model
Serving surfaces
Runvora Inference
Serverless Inference
Serving surfaces
Distributions
A downloadable artefact under this model's licence. Format, precision and size are properties of the artefact, not of the model.
Optimized Package
Available distributionServing Performance
Measured as ofEvery figure is measured under the conditions beside it. Read without them, a latency number claims more than it can.
| Metric | Typical value | Conditions |
|---|---|---|
| Output Tokens Per SecondSteady generated text-token rate after first token. | 97Token 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. | 112.8Token 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. | 103Token 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. | 87.9Token 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. | 1230Ms | 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. | 1060Ms | 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. | 1490Ms | 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. | 1270Ms | Capacity Mode: SHARED_ON_DEMANDDelivery Mode: STREAMINGInput Size Band: ~4K_TOKENSProcessing Tier: STANDARDConcurrency Band: C1 |
Applicable Benchmarks
View all 70 in Benchmarks →Benchmarks whose recorded requirements this model meets. Applicable means the requirements are met, not that the model was evaluated. No scores appear here.
- LiveBench11 definitions · 1 benchmark
- AppWorld2 definitions
- AI2 Reasoning Challenge3 definitions
Showing 3 of 23 families. Latest release per benchmark, up to 4 per family. Ordered by applicability, then name. Not a ranking.
126 not recorded. 115 have a required condition with no record for this model; 11 record no requirement at all. Nothing here says the model cannot meet them. View in Benchmarks
Resolved against the model baseline. A page that resolves a specific ModelSnapshot must re-resolve with that snapshot as the subject and say so.
Pricing Reference
Reference offering
Agent Makers · First Party Managed Api
| Meter | Basis | Rate |
|---|---|---|
| Input | Audited base input-token rate | $0.12 / 1000000Token |
| Output | Audited base output-token rate | $0.55 / 1000000Token |
| Cached Input | Audited base cached-input-token rate | $0.018 / 1000000Token |
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 opens on this model and prices a workload you state.
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.
- Effective fromPricingNormalUpcoming
Agent Makers pricing scheduled
Offering context: Agent Makers
Scheduled to take effect on 2026-09-15. Not yet effective.
- Effective fromPricingNormalUpcoming
Nimbrex Cloud pricing scheduled
Offering context: Nimbrex Cloud
Scheduled to take effect on 2026-09-15. Not yet effective.
- Effective fromPricingNormalUpcoming
Oryventa Models pricing scheduled
Offering context: Oryventa Models
Scheduled to take effect on 2026-09-15. Not yet effective.
- Effective fromPricingNormalUpcoming
Runvora Inference pricing scheduled
Offering context: Runvora Inference
Scheduled to take effect on 2026-09-15. Not yet effective.
- Effective fromAvailabilityNormal
Runvora Inference · Serverless Inference: Active
Offering context: Runvora Inference
Synthetic commercial activation.
- Effective fromAvailabilityMajor
Nimbrex Cloud · Cloud Managed Model: Active
Offering context: Nimbrex Cloud
Synthetic commercial activation.
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 of |
Use conditions (0)
None recordedNo condition constrains use of this model beyond its licence.Lifecycle & Lineage
Direct lineage
None recordedNo lineage relationship is recorded for this model.Recommended replacement for
None recordedNo replacement recommendation is recorded in either direction.Lifecycle history: Active on 2026-03-17.
Similar Industry Models
Captured as ofA positioning reference, not an equivalence claim. Each row states the axes it was drawn on, and covers only that part of this model's positioning.
Gemma 4 12B
Selected as a close current reference for Ctxdex Open General 4 Mini based on small open model, multimodal.
Checked 2026-09-14 · Medium confidence
Ministral 3 8B
Mistral AI
Selected as a close current reference for Ctxdex Open General 4 Mini based on small open model, text vision, efficient.
Checked 2026-09-14 · High confidence
Ministral 3 14B
Mistral AI
Selected as a reference current reference for Ctxdex Open General 4 Mini based on open model, text vision.
Checked 2026-09-14 · High confidence
Comparison method CTXDEX_COMPARABLES_V1.