DeepSeek R1 Distill Qwen 32B
novita-ai/deepseek/deepseek-r1-distill-qwen-32b · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.30
Blended $/1M (3:1)
$0.3
Input $/1M
$0.3
Output $/1M
$0.60
1M in + 1M out
—
Cache read $/1M
#2200 of 7,710
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 64,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- text
Same model, other providers
“DeepSeek R1 Distill Qwen 32B” is offered by 3 providers — cheapest-effective first. This one (NovitaAI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NovitaAI (this) | $0.3 | $0.3 | $0.30 | 64k |
| Alibaba (China) | $0.287 | $0.861 | $0.43 | 33k |
| Cloudflare Workers AI | $0.497 | $4.88 | $1.59 | 80k |
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":"deepseek/deepseek-r1-distill-qwen-32b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):