Qwen3 8B Fp8
Qwen3 8B Fp8 is a text model from 
Novita AI with a context window of 128K tokens and max output of 20K tokens. Pricing starts at 0.04 per million input tokens and 0.14 per million output tokens (cheapest at Fireworks AI).
Capabilities
✗ Vision✗ Function Calling✓ Reasoning✗ JSON Schema✓ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | novita/qwen/qwen3-8b-fp8 |
| Provider | Novita AI |
| Provider ID | novita |
| Mode | Text |
| Canonical Name | qwen-3-8b |
| Context Window | 128K tokens |
| Max Output | 20K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.000035 | 0.035 |
| Output Tokens | 0.000138 | 0.138 |
Price Comparison by Provider
Compare prices for Qwen3 8B Fp8 across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
| Novita AI | novita/qwen/qwen3-8b-fp8 | 0.035 | 0.138 |
| LlamaGate | llamagate/qwen3-8b | 0.040 | 0.140 |
 Fireworks AI | fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b | N/A | N/A |
All Variants
All available versions, regions, and API endpoints for Qwen3 8B Fp8.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| fireworks_ai/accounts/fireworks/models/qwen3-8b | Fireworks AI | Text | 0.200 | 0.200 | 41K | 41K | no | no |
| fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b | Fireworks AI | Rerank | N/A | N/A | 41K | 41K | no | no |
| llamagate/qwen3-8b | LlamaGate | Text | 0.040 | 0.140 | 33K | 8K | no | yes |
| novita/qwen/qwen3-8b-fp8 | Novita AI | Text | 0.035 | 0.138 | 128K | 20K | no | no |
| novita/qwen/qwen3-embedding-8b | Novita AI | Embedding | 0.070 | N/A | 33K | 4K | no | no |
| novita/qwen/qwen3-reranker-8b | Novita AI | Rerank | 0.050 | 0.050 | 33K | 4K | no | no |