ERNIE 4.5 VL 424B A47B
novita-ai/baidu/ernie-4.5-vl-424b-a47b · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: reasoning text image.
$0.63
Blended $/1M (3:1)
$0.42
Input $/1M
$1.25
Output $/1M
$1.67
1M in + 1M out
—
Cache read $/1M
#3277 of 7,708
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 123,000 tokens
- Max output
- 16,000 tokens
- Capabilities
- reasoning text image
Same model, other providers
“ERNIE 4.5 VL 424B A47B” is offered by 3 providers — cheapest-effective first. This one (NovitaAI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NovitaAI (this) | $0.42 | $1.25 | $0.63 | 123k |
| Jiekou.AI | $0.42 | $1.25 | $0.63 | 123k |
| DevPass (LLM Gateway) | $0.42 | $1.25 | $0.63 | 123k |
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":"baidu/ernie-4.5-vl-424b-a47b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):