jishie

Gemma 4 26B A4B IT

cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it · family gemma · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$0.15Blended $/1M (3:1)
$0.1Input $/1M
$0.3Output $/1M
$0.401M in + 1M out
Cache read $/1M
#1032 of 5,000Cheapest rank
Provider
Cloudflare Workers AI (cloudflare-workers-ai)
Context
256,000 tokens
Max output
16,384 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“Gemma 4 26B A4B IT” is offered by 9 providers — cheapest-effective first. OrcaRouter is the cheapest at $0.13 blended.

ProviderInputOutputBlendedContext
OrcaRouter$0.06$0.33$0.13262k
LLM Gateway$0.07$0.34$0.14262k
Kilo Gateway$0.07$0.34$0.14262k
Deep Infra$0.07$0.34$0.14262k
Cloudflare Workers AI (this)$0.1$0.3$0.15256k
Charm Hyper$0.116$0.408$0.19256k
SiliconFlow$0.12$0.4$0.19262k
OpenRouter$0.12$0.4$0.19262k
Hugging Face$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 Cloudflare Workers AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"@cf/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):