Gemma 3 27B
Google · Open weights · Released Mar 12, 2025 · google/gemma-3-27b-it
Best $0.08 in / $0.16 out via DeepInfra · fp8
131K contextVisionToolsStructured outputPrompt cachingOpen weights
Available from 4 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.08 | $0.16 | — | 131K | fp8 | ✕ | ✕ | 3/5 | 99.7% |
 Parasail | $0.08 | $0.45 | $0.04 | 131K | fp8 | 1.4s | 71 tok/s | 4/5 | 92.9% |
 Nebius | $0.10 | $0.30 | — | 110K | fp8 | 2.8s | 66 tok/s | 4/5 | 84.1% |
 Novita | $0.119 | $0.20 | — | 98K | bf16 | 1.8s | 42 tok/s | 4/5 | 97.4% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 4 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Aug 29, 2026endpoint removed · phala5 → 4
Aug 29, 2026context changed262144 → 131072
About
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Specifications
Context window131,072
Max output117,964
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedMar 12, 2025
Knowledge cutoff2024-08-31
TokenizerGemini
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/google/gemma-3-27b-it)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks14 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.