MODEL PROOF
Gemma 4 31B
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
Serving precision differs between offers.
MiMo-V2.6-Flash · Δ score 13 points · 15% lower measured price · $0.175 / 1M tokens
DeepSeek V4.1 Flash is a further stored option with these losses: no video input
- 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 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) |
|---|---|---|---|---|
| DeepInfradeepinfra/turbo Endpoint terms
| $0.090 | $0.340 | fp4 | 99.29% |
| CoreWeavecoreweave/fp4 Endpoint terms
| $0.100 | $0.340 | fp4 | 99.24% |
| Venicevenice/fp4 Endpoint terms
| $0.120 | $0.360 | fp4 | 99.41% |
| Chuteschutes/fp4 Endpoint terms
| $0.120 | $0.370 | fp4 | 94.20% |
| Crusoecrusoe/bf16 Endpoint terms
| $0.140 | $0.400 | bf16 | 99.48% |
| Novitanovita/bf16 Endpoint terms
| $0.140 | $0.400 | bf16 | 82.80% |
| Friendlifriendli Endpoint terms
| $0.140 | $0.400 | undeclared | 99.59% |
| Parasailparasail/fp8 Endpoint terms
| $0.150 | $0.400 | fp8 | 99.33% |
| DeepInfradeepinfra/fp8 Endpoint terms
| $0.200 | $0.400 | fp8 | 98.77% |
| Io Netio-net Endpoint terms
| $0.361 | $1.09 | undeclared | 99.28% |
| SambaNovasambanova Endpoint terms
| $0.380 | $1.15 | undeclared | 98.55% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.750 | $1.00 | fp8 | 76.52% |
| ModelRunmodelrun/fp4 Endpoint terms
| $0.750 | $1.00 | fp4 | 98.99% |
Independent scores
| LMArena Elo | 1443.4default |
|---|
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 |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | verified |
| Cross-checked | vendor page |
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
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.
[](https://undominated.ai/models/google__gemma-4-31b-it/)<a href="https://undominated.ai/models/google__gemma-4-31b-it/"><img src="https://undominated.ai/badge/google__gemma-4-31b-it.svg" alt="Gemma 4 31B — Undominated.ai dominance verdict" height="36"></a>Direct file: 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.
