Novita AI
currentqwen/qwen3-4b-fp8
Input
$0.03Output
$0.03Cache
—Context
128KMax output
20K- Reasoning
- Yes
- Tool calling
- No
- Structured output
- No
- Temperature
- Unknown
Historical price
← ModelsCompare model Estimate your workload cost
Alibaba · current
Qwen3 4B
Qwen3 4B is attributed to Alibaba in the catalog. It accepts text input and produces text output. Reported capabilities include reasoning.
Modalities
Token rates
UnavailableNo recent paired token rate available
Context
128KReleased
2025-04-29Knowledge cutoff
UnknownWhere to use it
1 observed offerings · token prices in USD per million where available
Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.
Capabilities and limits
- Input
- text
- Output
- text
- Max output
- 20K
- Weights
- Open (source-reported)
- Release
- 2025-04-29
- Knowledge cutoff
- Unknown
- Family
- qwen3
Reasoning
Provider-specific limits and support can differ.
Plan a model evaluation
Evaluate quality and latency on examples from your intended use before choosing a model.
Explore available evidenceModels to compare
Candidates match reported specifications; they are not tested replacements.
Model and price history
Price history (10 observations)
| Date | Provider | Input / output |
|---|---|---|
| 2026-10-09 | NovitaAI | $0.03 / $0.03 |
| 2026-10-09 | NovitaAI | $0.03 / $0.03 |
| 2026-10-08 | NovitaAI | $0.03 / $0.03 |
| 2026-10-07 | NovitaAI | $0.03 / $0.03 |
| 2026-09-22 | NovitaAI | $0.03 / $0.03 |
| 2026-09-21 | NovitaAI | $0.03 / $0.03 |
| 2026-09-20 | NovitaAI | $0.03 / $0.03 |
| 2026-09-19 | NovitaAI | $0.03 / $0.03 |
| 2026-09-18 | NovitaAI | $0.03 / $0.03 |
| 2026-09-17 | NovitaAI | $0.03 / $0.03 |