Last refreshed 2026-06-29. Next refresh: weekly.
Why use Qwen3-8B on Novita AI?
Novita AI offers Qwen3-8B with pay-as-you-go pricing at $0.04/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Compare Qwen3-8B across 4 providers to find the best fit for your use caseInput / 1M
$0.035
Output / 1M
$0.138
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: qwen3-8b-fp8Model ID
qwen3-8b-fp8Request example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "qwen3-8b-fp8", not the LLMReference slug "qwen3-8b".
Compare Qwen3-8B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.20 | $0.20 |
| OpenRouter | $0.05 | $0.40 |
| Novita AI | $0.04 | $0.14 |
| Featherless | $0.12 | $0.46 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.04 |
| Output tokens | $0.14 |
Capabilities
Structured Outputs
About Qwen3-8B
Compact base model in Qwen3 series, supporting 100+ languages with strong reasoning and coding capabilities.
Get Started
Model Specs
Released2025-08-15
Parameters8B
Context128k
ArchitectureDecoder Only