Gemma 4 26B A4B IT
kilo/google/gemma-4-26b-a4b-it · family gemma · in: image, text, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning image text video.
$0.07
Blended $/1M (3:1)
$0.04
Input $/1M
$0.15
Output $/1M
$0.19
1M in + 1M out
$0.01 −75%
Cache read $/1M
#729 of 8,504
Cheapest rank
- Provider
- Kilo Gateway (
kilo) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 235,929 tokens
- Capabilities
- tools reasoning image text video
Same model, other providers
“Gemma 4 26B A4B IT” is offered by 20 providers — cheapest-effective first. NaN is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NaN | free | free | $0.00 | 262k |
| Kilo Gateway (this) | $0.04 | $0.15 | $0.07 | 262k |
| OrcaRouter | $0.06 | $0.33 | $0.13 | 262k |
| DevPass (LLM Gateway) | $0.07 | $0.34 | $0.14 | 262k |
| Requesty | $0.07 | $0.34 | $0.14 | 262k |
| Deep Infra | $0.07 | $0.34 | $0.14 | 262k |
| OpenRouter | $0.09 | $0.3 | $0.14 | 262k |
| Cloudflare Workers AI | $0.1 | $0.3 | $0.15 | 256k |
| Charm Hyper | $0.098 | $0.334 | $0.16 | 256k |
| Amazon Bedrock | $0.13 | $0.4 | $0.20 | 262k |
| Novita AI | $0.13 | $0.4 | $0.20 | 262k |
| Hugging Face | $0.13 | $0.4 | $0.20 | 262k |
| SiliconFlow | $0.14 | $0.4 | $0.21 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Kilo Gateway 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):