jishie

Gemma 4 26B A4B

nano-gpt/google/gemma-4-26b-a4b-it · family gemma · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.18
Blended $/1M (3:1)
$0.12
Input $/1M
$0.38
Output $/1M
$0.50
1M in + 1M out
$0.06 −50%
Cache read $/1M
#1624 of 7,708
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
262,144 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Gemma 4 26B A4B” is offered by 4 providers — cheapest-effective first. CoreWeave is the cheapest at $0.15 blended.

ProviderInputOutputBlendedContext
CoreWeave$0.1$0.3$0.15262k
NanoGPT (this)$0.12$0.38$0.18262k
NovitaAI$0.13$0.4$0.20262k
Merge Gateway$0.13$0.4$0.20262k

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/gemma-4-26b-a4b-it","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