--- title: "Google: Gemma 3 4B — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/google__gemma-3-4b-it/ description: "Google: Gemma 3 4B: $0.050/M in, $0.100/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Google: Gemma 3 4B — price, capability and what beats it · Undominated.ai > Google: Gemma 3 4B: $0.050/M in, $0.100/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/google__gemma-3-4b-it/) [Cheaper alternatives](/alternatives/google__gemma-3-4b-it/) [Family](/families/gemma/) [Compare models](https://undominated.ai/compare/?models=google%2Fgemma-3-4b-it) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Gemma 3 4B Google · 13 Mar 2025 Balanced Summarise Chat Code gen Agentic FRONTIER ## Nothing is both better and cheaper under this workload. **$0.063** / 1M tokens Balanced · 3 tokens in per 1 out Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,290.8 ± 9.23 · 4,171 votes Context window 131.07K Maximum output 16.38K Input modalities text, image Output modalities text Published input price $0.050 / 1M tokens Published output price $0.100 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from DeepInfra: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (bf16), at its standard rate. The maker’s own precision is not known. Every price dimension · USD per million tokens | Input | $0.050 /M | | --- | --- | | Output | $0.100 /M | | Cached input | Unknown /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. 1 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DeepInfra deepinfra/bf16 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 16,384 tokens Tools Not listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.050 | Output $0.100 | Precision bf16 | Uptime (1d) 100.00% | ### Independent scores | LMArena Elo | 1290.8 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. ### Capability | Context window | 131K | | --- | --- | | Max output | 16K | | Input modes | text, image | | Tool use | no | | Reasoning | no | | Knowledge cutoff | 2024-08-31 | | Open weights | Unknown | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | 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,... ## Questions this page answers What does Gemma 3 4B cost? $0.050/M in, $0.100/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Gemma 3 4B have an independent quality score? Gemma 3 4B has an LMArena score in this catalogue. What beats Gemma 3 4B? Nothing is both better and cheaper than Gemma 3 4B. Does this page use Artificial Analysis scores for Gemma 3 4B? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Google: Gemma 3 4B. Balanced workload. Frontier. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Side by side [gpt-oss-20b](/compare/google__gemma-3-4b-it--vs--openai__gpt-oss-20b/) - Nearby on the capability axis [GPT-4o (2024-05-13)](/models/openai__gpt-4o-2024-05-13/) - Same vendor [Gemma 3 12B](/models/google__gemma-3-12b-it/) - Google models [Google](/providers/google/) - Where this model appears [frontier](/frontier/) - Side by side [gpt-oss-120b](/compare/google__gemma-3-4b-it--vs--openai__gpt-oss-120b/) - Nearby on the capability axis [gpt-oss-20b](/models/openai__gpt-oss-20b/) - Same vendor [Gemma 2 27B](/models/google__gemma-2-27b-it/) - Where this model appears [knee](/knee/) - Nearby on the capability axis [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) - Same vendor [Gemma 3 27B](/models/google__gemma-3-27b-it/) - Where this model appears [wire](/wire/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Gemma 3 4B — Undominated.ai dominance verdict](https://undominated.ai/badge/google__gemma-3-4b-it.svg)](https://undominated.ai/models/google__gemma-3-4b-it/) HTML Copy Gemma 3 4B — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/google__gemma-3-4b-it.svg](https://undominated.ai/badge/google__gemma-3-4b-it.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)