Google

Gemma 3 27B

131K ctxTextImage

Released Mar 12, 2025 · 38B tokens this week · 4 providers

Overview

Google's open-weight model with vision input and a permissive licence. A good self-hostable option for multilingual chat and light multimodal work. Small enough to fine-tune on a single node.

translationroleplayacademia

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	131K	8K	$0.10	$0.20	520ms	105	98.70%	fp8
Novita AI	131K	8K	$0.11	$0.22	560ms	92	98.50%	fp8
Together AI	131K	8K	$0.11	$0.23	195ms	130	99.42%	Full
Google AI Studio	33K	8K	$0.12	$0.24	390ms	150	99.80%	Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Gemma 3 27B$0.17

DeepSeek V3.2$0.37

Grok 4 Fast$0.42

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-27b",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'