Gemma 3 12B
Newer version available: Gemma 4 12B IT
Cheapest of 6 routes · Novita AI
Cheapest of 6 routes · Novita AI
About
Gemma 3 12B is Google DeepMind's Gemma 3 model. It offers a 128K-token context window with weights openly available for self-hosting.
Providers(6)
Compare all 6Compare API pricing across 6 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Novita AI | $0.050 | $0.100 | Serverless |
| GCP Vertex AI | $0.040 | $0.130 | Serverless |
| OpenRouter | $0.050 | $0.150 | Serverless |
| Fireworks AI | $0.200 | $0.200 | Serverless |
| AWS Bedrock | $0.300 | $0.300 | Serverless Scheduled retirement: March 30, 2027 |
| Cloudflare Workers AI | $0.345 | $0.556 | Serverless |
Available via routers & gateways(14)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native prompt router that predicts each model's performance per request and routes between two models of the same family (Anthropic Claude, Meta Llama or Amazon Nova).
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache-2.0 open-source platform with a managed hosted tier for logging and analytics.
Capabilities
Benchmark peer barsfor RAG
Benchmark scores(3)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 30.4 | v4Observed 2026-10-26 | Configuration: Gemma-3-12b-it (Prompt) Harness: BFCL V4 official evaluation (gorilla berkeley-function-call-leaderboard), Prompt mode Evaluator: Gorilla LLM team (UC Berkeley) Confidence: confirmed Notes: BFCL V4 leaderboard (Last Updated 2026-04-12), entry 'Gemma-3-12b-it (Prompt)': rank 66, Overall Acc 30.43%; Multi Turn 5.75%, Web Search 4.00%, Memory 27.53%, Non-Live AST 79.44%, Live 74.24%, Irrelevance 70.29%. Retrieved 2026-10-26. | ||
| 57.1 | RULER (128K) (accuracy)Observed 2026-10-26 | — | ||
| 1331.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Gemma 3 12B IT Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3 12B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 192 of 416, rating 1331.1 (95% CI 1308.0-1354.1), 600 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.
Compare Gemma 3 12B with other models
- Gemma 3 12B vs Qwen3.5-9B86
- Gemma 3 12B vs Llama 3.1 Swallow 8B Instruct84
- Gemma 3 12B vs Nemotron 3 Content Safety48
- Gemma 3 12B vs Phi-4 Mini Flash Reasoning44
- Gemma 3 12B vs Mistral Nemotron26
- Gemma 3 12B vs Mistral Medium 318
- Gemma 3 12B vs Trinity-Large-Preview16
- Gemma 3 12B vs Llama 3.1 NemoGuard 8B Content Safety10