Phi 4 Multimodal
nano-gpt/phi-4-multimodal-instruct · family phi · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.08
Blended $/1M (3:1)
$0.07
Input $/1M
$0.11
Output $/1M
$0.18
1M in + 1M out
$0.035 −50%
Cache read $/1M
#849 of 7,710
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- text
Same model, other providers
“Phi 4 Multimodal” is offered by 2 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 128k |
| NanoGPT (this) | $0.07 | $0.11 | $0.08 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"phi-4-multimodal-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):