jishie

Qwen3.6 Flash

nano-gpt/qwen/qwen3.6-flash · family qwen3.6 · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: text image video.

$0.43
Blended $/1M (3:1)
$0.19
Input $/1M
$1.16
Output $/1M
$1.35
1M in + 1M out
$0.02 −89%
Cache read $/1M
#2449 of 7,322
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
991,808 tokens
Max output
65,536 tokens
Capabilities
text image video

Same model, other providers

“Qwen3.6 Flash” is offered by 21 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Merge Gateway$0.165$0.99$0.371M
AIHubMix$0.17$1.01$0.38991k
Alibaba Coding Plan (China)$0.1875$1.13$0.421M
Alibaba (China)$0.1875$1.13$0.421M
Pioneer$0.1875$1.13$0.421M
Alibaba$0.1875$1.13$0.421M
Kilo Gateway$0.1875$1.13$0.421M
Alibaba Coding Plan$0.1875$1.13$0.421M
OpenRouter$0.1875$1.13$0.421M
302.AI$0.188$1.13$0.421M
NanoGPT (this)$0.19$1.16$0.43992k

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":"qwen/qwen3.6-flash","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all NanoGPT models · model index · JSON