GoogleReasoningReleased 2 April 2026
Gemma 4 31B pricing, context and benchmark
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
262K
Input context
262K
Output context
$0.1
Official input
$0.34
Official output
4
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Gemma 4 31B |
| Model ID | google/gemma-4-31b-it |
| Provider | |
| Release date | 2 April 2026 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 262,141 tokens |
| Official input pricing | $0.1 per 1M tokens |
| Official output pricing | $0.34 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $0.1 per 1M (cheapest route) |
| Market output pricing | $0.34 per 1M (cheapest route) |
| Highest route pricing | $0.135 in, $0.51 out per 1M |
| Input modalities | image · text · video |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Gemma |
| Provider routes | 8 endpoints |
| Artificial Analysis index | 4 (#9 of 10) |
| Speed | 36 tokens/s, 26.71s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.1 in |
| Image | ✓ yes | no | $0.1 in |
| Audio | no | no | not supported |
| Video | ✓ yes | no | $0.1 in |
| File (PDF) | no | no | not supported |
02 · Overview
What is Gemma 4 31B?
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...
Gemma 4 31B carries a 262K token window, uses the Gemma tokenizer and is served by Google. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released2 April 2026
| Property | Lyria 3 Clip Preview | Gemma 4 31B | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 1.05M | 262K | Changed |
| Max output | 66K | 262K | Changed |
| Input price | Free | $0.1 | Higher |
| Output price | Free | $0.34 | Higher |
| Input modalities | text, image | image, text, video | Unchanged |
| AA index | n/a | 4 | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.
06 · Benchmarks
Benchmark results and performance
Artificial Analysis Intelligence Index v5.0.1 blends nine evaluations. Gemma 4 31B scores 4 , ranking #9 of 10.
Intelligence index
4
#9 of 10
Cost per task
n/a
weighted average per index task
Time per task
n/a
inference time
Output speed
36
tokens per second
Index score and cost per task
Scale: index 0 to 70, cost 0 to $20. Sub scores are not published per evaluation, so none are invented here.
07 · Use cases
What can you do with Gemma 4 31B?
Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
09 · Pricing
Gemma 4 31B pricing
Official pricing
List price
$0.1 / 1M in
$0.34 / 1M out
- 262K context
- image, text, video input
Cheapest route
$0.1 / 1M in
$0.34 / 1M out
- 8 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$0.135 / 1M in
$0.51 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| CoreWeave | standard | $0.1 | $0.34 | $0.1 | 100.0% |
| Venice | standard | $0.12 | $0.36 | $0.09 | 99.6% |
| Chutes | standard | $0.12 | $0.37 | $0.012 | 99.9% |
| DeepInfra | priority | $0.135 | $0.51 | $0.075 | 99.6% |
| DekaLLM | standard | $0.14 | $0.4 | $0.05 | 99.6% |
| Crusoe | standard | $0.14 | $0.4 | $0.14 | 99.9% |
| Friendli | standard | $0.14 | $0.4 | n/a | 100.0% |
| Novita | standard | $0.14 | $0.4 | n/a | 83.1% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0025 | $1.26 | 1193 |
| List price | $0.0025 | $1.26 | 1193 |
| Highest route | $0.0035 | $1.73 | 1646 |
10 · Developers
API and developer information
| Model ID | google/gemma-4-31b-it |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+video->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 262,141 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-31b-it",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 262,141 tokens per request. Long deliverables have to be chunked. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Gemma 4 31B vs other Google models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Gemma 4 31B | 262K | $0.1 | $0.34 | 4 | 2026 |
| Gemini 3.1 Pro Preview | 1.05M | $2 | $12 | n/a | 2026 |
| Gemini 4 Argon | 1.05M | $2 | $10 | 50 | Oct 2026 |
| Gemini 4 Carbon | 1.05M | $2 | $10 | n/a | 2026 |
| Gemini 3.1 Pro Preview Custom Tools | 1.05M | $2 | $12 | n/a | 2026 |
| Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2 | $12 | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Google and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Gemma 4 31B questions, answered
Gemma 4 31B is a reasoning model from Google, released 2 April 2026. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
✦
Start chatting with Gemma 4 31B
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.