Qwen 2.5 72B Instruct
novita-ai/qwen/qwen-2.5-72b-instruct · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.39
Blended $/1M (3:1)
$0.38
Input $/1M
$0.4
Output $/1M
$0.78
1M in + 1M out
—
Cache read $/1M
#2429 of 7,713
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 32,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools text
Same model, other providers
“Qwen 2.5 72B Instruct” is offered by 2 providers — cheapest-effective first. Abacus is the cheapest at $0.18 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Abacus | $0.11 | $0.38 | $0.18 | 128k |
| NovitaAI (this) | $0.38 | $0.4 | $0.39 | 32k |
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/qwen-2.5-72b-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):