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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Model card on Hugging Face- Input / output price
- $0.00 / $0.00 per 1M
- Context
- 262K tokens
- Released
- Apr 2, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
12 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Google Gemini AI google_gemini_ai/gemma-4-31b-it | $0.00/M | $0.00/M |
Featherless featherless/gemma-4-31b-it | $0.12/M | $0.36/M |
Chutes chutes/gemma-4-31b-it | $0.12/M | $0.37/M |
Nextbit256 nextbit256/gemma4:31b | $0.125/M | $0.34/M |
Concentrate concentrate/gemma-4-31b | $0.14/M | $0.40/M |
FriendliAI friendliai/gemma-4-31b-it | $0.14/M | $0.40/M |
NovitaRetiring novita/gemma-4-31b-it | $0.14/M | $0.40/M |
Parasail parasail/gemma-4-31b-it | $0.15/M | $0.40/M |
Prime Intellect prime_intellect/google/gemma-4-31b-it | $0.20/M | $0.335/M |
DeepInfra deepinfra/gemma-4-31b-it | $0.20/M | $0.40/M |
IO.net ionet/google/gemma-4-31b-it | $0.349/M | $0.632/M |
OpenRouter openrouter/gemma-4-31b-it | $0.20/M | $0.40/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 12 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.16 per 1M
- Average output
- $0.37 per 1M
- Average cache read
- $0.13 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better112tokens/sacross providers
Time to first token
Lower is better3.6sacross providers
Response latency
Lower is better11sacross providers
Benchmarks
The Respan Index plus 15 published scores from 5 sources, each linked to where it was published.
18.7/ 100
Respan Index#140 of 176
- 140Gemma 4 31B18.7
- 141Qwen3 235B-A22B Thinking 250718.5
- 141Gemini 2.5 Flash18.5
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBench v6Google | 80% | Apr 2, 2026 | |
| WeirdMLHåvard Tveit Ihle | 52.3% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondGoogle | 84.3% | Apr 2, 2026 | |
| GPQA DiamondEpoch AI | 75.8% | Epoch AI | Oct 5, 2026 |
| Humanity's Last Exam (no tools)Google | 19.5% | Apr 2, 2026 | |
| Chess PuzzlesEpoch AI | 5% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026 (no tools)Google | 89.2% | Apr 2, 2026 | |
| OTIS Mock AIME 2024-2025Epoch AI | 73.3% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-ProGoogle | 85.2% | Apr 2, 2026 | |
| SimpleQA VerifiedEpoch AI | 10.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1452 Elo · #64 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1370 Elo · #96 of 124 | LMArena | Nov 20, 2026 |
| LMArena VisionLMArena | 1265 Elo · #31 of 91 | LMArena | Nov 19, 2026 |
Compare Gemma 4 31B: Gemma 4 31B vs Gemini 4 Argon, Gemma 4 31B vs Gemma 4 26B A4B, Gemma 4 31B vs Gemini 4 Neon, Gemma 4 31B vs Gemini 4 Carbon, Gemma 4 31B vs Gemini 4 Hydrogen, Gemma 4 31B vs Gemini 3.8 Flash
Apps
Use Gemma 4 31B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 4 31B FAQ
Short answers, built from the data on this page.
Gemma 4 31B is a model from Google Gemini AI, released on Apr 2, 2026. 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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
On the Respan gateway, Gemma 4 31B costs from $0.00 per 1M input tokens and $0.00 per 1M output tokens on Google Gemini AI, after gateway discounts. Averaged across its 12 providers, it costs $0.16 per 1M input tokens and $0.37 per 1M output tokens.
Gemma 4 31B is available through 12 providers: Google Gemini AI, Featherless, Chutes, Nextbit256, Concentrate, FriendliAI, and 6 more.
Gemma 4 31B accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemma-4-31b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemma 4 31B scores 18.7 out of 100 on the Respan Index v1.1, ranking #140 of 176 models. By category: Coding 7.8, Agents 12.5 (estimated), Reasoning 19.7, Knowledge & language 11.0, and Human preference 50.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Gemma 4 31B has 15 published benchmark scores, including LiveCodeBench v6 80%, GPQA Diamond 84.3%, and AIME 2026 (no tools) 89.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.