Gemini 3.7 Flash
nano-gpt/google/gemini-3.7-flash · family gemini-flash · in: text, image, video, audio, pdf → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtextimagevideoaudiopdf.
$0.75Blended $/1M (3:1)
$0.375Input $/1M
$1.875Output $/1M
$2.251M in + 1M out
$0.0375 −90%Cache read $/1M
#2749 of 5,851Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Capabilities
- toolsreasoningtextimagevideoaudiopdf
Same model, other providers
“Gemini 3.7 Flash” is offered by 10 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT (this) | $0.375 | $1.875 | $0.75 | 1049k |
| OpenRouter | $0.375 | $1.875 | $0.75 | 1049k |
| Vertex | $0.75 | $3.75 | $1.50 | 1049k |
| $0.75 | $3.75 | $1.50 | 1049k | |
| Merge Gateway | $0.75 | $3.75 | $1.50 | 1049k |
| Requesty | $0.75 | $3.75 | $1.50 | 1049k |
| Vercel AI Gateway | $0.75 | $3.75 | $1.50 | 1000k |
| LLM Gateway | $0.75 | $3.75 | $1.50 | 1049k |
| Kilo Gateway | $0.75 | $3.75 | $1.50 | 1049k |
| OpenCode Zen | $1.5 | $7.5 | $3.00 | 1049k |
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":"google/gemini-3.7-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):