Qwen3 32B
novita-ai/qwen/qwen3-32b-fp8 · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.
$0.19
Blended $/1M (3:1)
$0.1
Input $/1M
$0.45
Output $/1M
$0.55
1M in + 1M out
—
Cache read $/1M
#1653 of 7,712
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 40,960 tokens
- Max output
- 20,000 tokens
- Capabilities
- reasoning text
Same model, other providers
“Qwen3 32B” is offered by 16 providers — cheapest-effective first. Deep Infra is the cheapest at $0.13 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.08 | $0.28 | $0.13 | 41k |
| Kilo Gateway | $0.08 | $0.28 | $0.13 | 41k |
| OpenRouter | $0.08 | $0.28 | $0.13 | 131k |
| Abacus | $0.09 | $0.29 | $0.14 | 131k |
| NovitaAI (this) | $0.1 | $0.45 | $0.19 | 41k |
| Jiekou.AI | $0.1 | $0.45 | $0.19 | 41k |
| Merge Gateway | $0.15 | $0.6 | $0.26 | 131k |
| Amazon Bedrock | $0.15 | $0.6 | $0.26 | 33k |
| Cortecs | $0.179 | $0.697 | $0.31 | 16k |
| DigitalOcean | $0.25 | $0.55 | $0.33 | 33k |
| Hugging Face | $0.29 | $0.59 | $0.36 | 131k |
| Helicone | $0.29 | $0.59 | $0.36 | 131k |
| DevPass (LLM Gateway) | $0.36 | $0.87 | $0.49 | 41k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NovitaAI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3-32b-fp8","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):