Gemma 3 1B Instruct
Cheapest of 2 routes · Fireworks AI
Cheapest of 2 routes · Fireworks AI
About
Gemma 3 1B Instruct is Google DeepMind's Gemma 3 model. It offers a 32K-token context window with weights openly available for self-hosting.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.100 | $0.100 | Serverless |
| NVIDIA NIM | - | - | ServerlessPartial |
Available via routers & gateways(2)
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.
NVIDIA LLM Router Blueprint
RouterNVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; deprecated in favor of NVIDIA NeMo Switchyard.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor JSON / Tool use
Benchmark scores(1)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 7.2 | v4Observed 2026-10-26 | Configuration: Gemma-3-1b-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-3-1b-it (Prompt)': rank 109, Overall Acc 7.17%; Multi Turn 0.00%, Web Search 0.00%, Memory 3.23%, Non-Live AST 20.21%, Live 11.84%, Irrelevance 33.18%. Retrieved 2026-10-26. |
Migration checks
No linked migration route is available for this model yet.