--- title: "Google: Gemma 4 31B — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/google__gemma-4-31b-it/ description: "Google: Gemma 4 31B: $0.140/M in, $0.400/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Google: Gemma 4 31B — price, capability and what beats it · Undominated.ai > Google: Gemma 4 31B: $0.140/M in, $0.400/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/google__gemma-4-31b-it/) [Cheaper alternatives](/alternatives/google__gemma-4-31b-it/) [Family](/families/gemma/) [Compare models](https://undominated.ai/compare/?models=google%2Fgemma-4-31b-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 4 31B Google · 02 Apr 2026 · apache-2.0 Balanced Summarise Chat Code gen Agentic BETTER VALUE OPTION ## A stored alternative has an equal-or-higher measured score and an equal-or-lower price. **$0.205** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) · Δ score 13 points · 15% lower measured price · $0.175 / 1M tokens [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) is a further stored option with these losses: no video input Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,443.4 ± 7.4 · 6,133 votes Context window 262.14K Maximum output 16.38K Input modalities image, text, video Output modalities text Published input price $0.140 / 1M tokens Published output price $0.400 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Crusoe: 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. Cheaper right now: $0.153/M at DeepInfra — delivery tier (turbo) · 4-bit It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.140 /M | | --- | --- | | Output | $0.400 /M | | Cached input | $0.140 /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. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from Crusoe. 13 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/turbo Endpoint terms Cached input /M $0.050 Context limit 262,144 tokens Output limit 16,384 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.90% | Input $0.090 | Output $0.340 | Precision fp4 | Uptime (1d) 99.29% | | Seller CoreWeave coreweave/fp4 Endpoint terms Cached input /M $0.100 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.55% | Input $0.100 | Output $0.340 | Precision fp4 | Uptime (1d) 99.24% | | Seller Venice venice/fp4 Endpoint terms Cached input /M $0.090 Context limit 256,000 tokens Output limit 8,192 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.14% | Input $0.120 | Output $0.360 | Precision fp4 | Uptime (1d) 99.41% | | Seller Chutes chutes/fp4 Endpoint terms Cached input /M $0.012 Context limit 131,072 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 95.93% | Input $0.120 | Output $0.370 | Precision fp4 | Uptime (1d) 94.20% | | Seller Crusoe crusoe/bf16 Endpoint terms Cached input /M $0.140 Context limit 262,144 tokens Output limit 262,141 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.89% | Input $0.140 | Output $0.400 | Precision bf16 | Uptime (1d) 99.48% | | Seller Novita novita/bf16 Endpoint terms Cached input /M Unknown Context limit 262,144 tokens Output limit 131,072 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 81.87% | Input $0.140 | Output $0.400 | Precision bf16 | Uptime (1d) 82.80% | | Seller Friendli friendli Endpoint terms Cached input /M Unknown Context limit 262,144 tokens Output limit 8,192 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.93% | Input $0.140 | Output $0.400 | Precision undeclared | Uptime (1d) 99.59% | | Seller Parasail parasail/fp8 Endpoint terms Cached input /M $0.060 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.96% | Input $0.150 | Output $0.400 | Precision fp8 | Uptime (1d) 99.33% | | Seller DeepInfra deepinfra/fp8 Endpoint terms Cached input /M Unknown Context limit 262,144 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.52% | Input $0.200 | Output $0.400 | Precision fp8 | Uptime (1d) 98.77% | | Seller Io Net io-net Endpoint terms Cached input /M $0.181 Context limit 262,144 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount 5% · already included in these rates Uptime · last 30 minutes 99.35% | Input $0.361 | Output $1.09 | Precision undeclared | Uptime (1d) 99.28% | | Seller SambaNova sambanova Endpoint terms Cached input /M Unknown Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 97.95% | Input $0.380 | Output $1.15 | Precision undeclared | Uptime (1d) 98.55% | | Seller SiliconFlow siliconflow/fp8 Endpoint terms Cached input /M $0.250 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.18% | Input $0.750 | Output $1.00 | Precision fp8 | Uptime (1d) 76.52% | | Seller ModelRun modelrun/fp4 Endpoint terms Cached input /M $0.200 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.36% | Input $0.750 | Output $1.00 | Precision fp4 | Uptime (1d) 98.99% | ### Independent scores | LMArena Elo | 1443.4 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. ### Capability | Context window | 262K | | --- | --- | | Max output | 16K | | Input modes | image, text, video | | Tool use | yes | | Reasoning | optional | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | | Cross-checked | [vendor page](https://openrouter.ai/api/v1/models) | Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function... ## Questions this page answers What does Gemma 4 31B cost? $0.140/M in, $0.400/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Gemma 4 31B have an independent quality score? Gemma 4 31B has an LMArena score in this catalogue. What beats Gemma 4 31B? MiMo-V2.6-Flash has an equal-or-higher measured score and an equal-or-lower price. Does this page use Artificial Analysis scores for Gemma 4 31B? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Is the cheapest Gemma 4 31B endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from Crusoe. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Google: Gemma 4 31B. Balanced workload. Better value option available. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Both better and cheaper [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) - Higher score and cheaper, with a named trade [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) - Side by side [Gemma 4 26B A4B](/compare/google__gemma-4-26b-a4b-it--vs--google__gemma-4-31b-it/) - Nearby on the capability axis [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) - Same vendor [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) - Google models [Google](/providers/google/) - Where this model appears [wire](/wire/) - Side by side [MiMo-V2.5-Pro](/compare/google__gemma-4-31b-it--vs--xiaomi__mimo-v2.5-pro/) - Nearby on the capability axis [Claude Sonnet 5](/models/anthropic__claude-sonnet-5/) - Same vendor [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) - Where this model appears [self-host](/self-host/) - Nearby on the capability axis [GPT-6 Astra](/models/openai__gpt-6-astra/) ## 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 4 31B — Undominated.ai dominance verdict](https://undominated.ai/badge/google__gemma-4-31b-it.svg)](https://undominated.ai/models/google__gemma-4-31b-it/) HTML Copy Gemma 4 31B — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/google__gemma-4-31b-it.svg](https://undominated.ai/badge/google__gemma-4-31b-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/)