Gemini 2.5 Flash Preview Thinking
nano-gpt/gemini-2.5-flash-preview-04-17:thinking · family gemini · in: text, image, audio → out: text · price provider-declared (via models.dev). Capabilities: reasoning text image audio.
$0.99
Blended $/1M (3:1)
$0.15
Input $/1M
$3.5
Output $/1M
$3.65
1M in + 1M out
$0.015 −90%
Cache read $/1M
#3998 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Capabilities
- reasoning text image audio
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":"gemini-2.5-flash-preview-04-17:thinking","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):