KI‑Modell‑Intelligenz

paligemma

nvidia/paligemma

Von NVIDIA · veröffentlicht 2024-05-14

⚠ Dies ist ein Community-Finetune oder Derivat — keine offizielle Anbieter-Veröffentlichung.

Unbekannt
Eingabe / 1 Mio. Tokens
Unbekannt
Ausgabe / 1 Mio. Tokens
128K
Kontextfenster
8K
Max. Ausgabe

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Fähigkeiten

✗ Tool Calling✗ Reasoning? Strukturierte Ausgabe✓ Anhänge✓ Offene Gewichte✓ Temperatur-Steuerung
Modalitäten: Eingabe text, image · Ausgabe text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding3
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)2/20
  • Provider availability1/10
Agents6
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit5/15
  • Provider availability1/10
JSON / structured output10
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control10/10
  • Price-friendly for high-volume0/20
Cost efficiency0
  • Has published price0/100
Long context35
  • Context window (100K → 2M)35/90
  • Has published price for full window0/10
Vision68
  • Accepts image input50/50
  • Context window (10K → 1M)17/30
  • Has published price0/10
  • Provider availability1/10
Production-readiness30
  • Number of independent providers5/40
  • Has published per-token price0/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)0/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

This model has no published per-token price, so we can't compute a cost estimate. See the provider's official pricing page for current rates.

Bei 1 Anbietern verfügbar

AnbieterAnbieter-Modell-IDEingabe / 1MAusgabe / 1MKontextVeröffentlicht
Nvidia
nvidia
google/google-paligemmaUnknownUnknown128K2024-05-14

Frequently asked questions

How much does paligemma cost?

paligemma does not have a publicly published per-token price in our data source. This usually means it is gated behind enterprise sales or invite access. Check NVIDIA's official pricing page for the most current rates.

What is the context window of paligemma?

paligemma has a context window of 128K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.

Does paligemma support tool calling?

No. paligemma does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does paligemma support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for paligemma in our data source. Verify with NVIDIA's official documentation before relying on it in production.

Can paligemma accept image input?

Yes. paligemma accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check NVIDIA's docs for the exact rule.

Is paligemma open-weight?

Yes. paligemma's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to paligemma?

If paligemma doesn't fit, consider Nemotron 3 Super, nemotron-3-nano-30b-a3b, nvidia-nemotron-nano-9b-v2. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More NVIDIA models

Capability lists this model is in

See also

Zuletzt aktualisiert:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.