Gemini 3.5 Flash
prime/google/gemini-3.5-flash · family gemini-flash · in: text, image, video, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio.
$3.38
Blended $/1M (3:1)
$1.5
Input $/1M
$9
Output $/1M
$10.50
1M in + 1M out
—
Cache read $/1M
#6119 of 8,071
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image video audio
Same model, other providers
“Gemini 3.5 Flash” is offered by 32 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 1M |
| UnoRouter | $0.1857 | $1.11 | $0.42 | 1M |
| Kilo Gateway | $0.75 | $4.5 | $1.69 | 1M |
| Prime Inference (this) | $1.5 | $9 | $3.38 | 1M |
| NanoGPT | $1.5 | $9 | $3.38 | 1M |
| NEAR AI Cloud | $1.5 | $9 | $3.38 | 1M |
| Abacus | $1.5 | $9 | $3.38 | 1M |
| 302.AI | $1.5 | $9 | $3.38 | 1M |
| OpenRouter | $1.5 | $9 | $3.38 | 1M |
| ZenMux | $1.5 | $9 | $3.38 | 1M |
| Impossibl | $1.5 | $9 | $3.38 | 1M |
| $1.5 | $9 | $3.38 | 1M | |
| Vercel AI Gateway | $1.5 | $9 | $3.38 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"google/gemini-3.5-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):