Gemma 4 31B API Benchmarks, Pricing & Provider Data
Compare Gemma 4 31B with another model
Choose a model to open its comparison page.
Gemma 4 31B API pricing covers 18 API providers, from $0.0010/request to $375.00/M. Gemma 4 31B free API options are available from 2 providers.
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, nat...
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Total parameters
- 31B
- Released
- Apr 2026
- Tokenizer
- Gemma
- Architecture
- text+image+video->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
OpenRouter endpoints
15 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
ModelRun modelrun/fp4 | $0.750/M | $1/M | 100.0% | — | — | undefined tokens / undefined tokens |
Cerebras cerebras/fp16 | $0.990/M | $1.49/M | 100.0% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/turbo | $0.090/M | $0.340/M | 99.9% | — | — | undefined tokens / undefined tokens |
CoreWeave coreweave/fp4 | $0.100/M | $0.340/M | 99.7% | — | — | undefined tokens / undefined tokens |
Friendli friendli | $0.140/M | $0.400/M | 99.6% | — | — | undefined tokens / undefined tokens |
Parasail parasail/fp8 | $0.150/M | $0.400/M | 99.4% | — | — | undefined tokens / undefined tokens |
Venice venice/bf16 | $0.120/M | $0.360/M | 99.4% | — | — | undefined tokens / undefined tokens |
Together together | $0.390/M | $0.970/M | 98.3% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp8 | $0.130/M | $0.380/M | 97.4% | — | — | undefined tokens / undefined tokens |
SambaNova sambanova | $0.380/M | $1.15/M | 96.7% | — | — | undefined tokens / undefined tokens |
Chutes chutes/fp4 | $0.120/M | $0.370/M | 96.5% | — | — | undefined tokens / undefined tokens |
Novita novita/bf16 | $0.140/M | $0.400/M | 93.9% | — | — | undefined tokens / undefined tokens |
Crusoe crusoe | $0.140/M | $0.400/M | 93.5% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $0.130/M | $0.400/M | 93.5% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/ultra | $0.270/M | $0.760/M | 52.1% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Gemma 4 31B API pricing across 16 providers. Prices range from $0.0010/request to $375.00/M. CM-API 公益站 offers the lowest rate at $0.0010/request. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gemma-4-31b-it | Model | $0.0096/M | $0.027/M | — | — | — | |
L1 100% | gemma-4-31b-it | default | $0.130/M Cache read$0.026/M | $0.380/M | — | — | — | |
L1 99% | google/gemma-4-31b-it:free | free | $0.0010/request | - | — | — | — | |
L1 99% | gemma-4-31b-it | default | $0.0014/request | - | — | — | — | |
L1 100% L2 0% | gemma-4-31b-it | default | $1.00/M | $3.00/M | — | — | — | |
L1 100% | google/gemma-4-31b-it | default | $10.00/M | $10.00/M | — | — | — | |
L1 100% | gemma-4-31b-it | default | $10.00/M | $10.00/M | — | — | — | |
L1 100% | google/gemma-4-31b-it:free | default | $375.00/M | $375.00/M | — | — | — | |
L1 97% | google/gemma-4-31B-it | 国产模型 | $0.390/M Cache read$0.078/M | $0.970/M | — | — | — | |
L1 81% | google/gemma-4-31B-it | CC | $2.04/M | $5.84/M | — | — | — | |
Dext API Free | L1 66% | gemma-4-31b-it | 公益 | Free | Free | — | — | — |
L1 100% | google/gemma-4-31b-it | default | $0.015/M Cache read$0.011/M | $0.048/M | — | — | — | |
91VIP API Free | L1 99% | google/gemma-4-31b-it | default | Free | Free | — | — | — |
L1 68% | google/gemma-4-31b-it | default | $75.00/M | $75.00/M | — | — | — | |
L1 0% | google/gemma-4-31b-it:free | default | $0.010/request | - | — | — | — | |
L1 0% | google/gemma-4-31b-it | default | $0.300/M | $0.300/M | — | — | — | |
L1 0% | gemma-4-31b-it | default | $1.00/M | $3.00/M | — | — | — | |
L1 0% | google/gemma-4-31b-it:free | OpenAI | $10.27/M | $10.27/M | — | — | — |
Alternatives & Similar Models
DeepSeek V3.2
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
MiniMax M2.7
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
MiniMax M2.5
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
Frequently Asked Questions
- What benchmark data does Gemma 4 31B include?
- LMSpeed shows Gemma 4 31B benchmark context, API price, output speed, first-token latency, and provider data across 18 providers when those signals are available.
- What is the Gemma 4 31B API price?
- Gemma 4 31B has pricing from 18 providers, ranging from $0.0010/request to $375.00/M. CM-API 公益站 has the lowest listed price.
- What does the Gemma 4 31B API pricing table include?
- The Gemma 4 31B API pricing table compares 18 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Gemma 4 31B API pricing?
- CM-API 公益站 currently has the lowest listed Gemma 4 31B price at $0.0010/request across 18 providers.
- Is Gemma 4 31B API free?
- Yes, Gemma 4 31B free API options are available through 2 providerundefined other undefined} on LMSpeed, including Dext API, 91VIP API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Gemma 4 31B free API access?
- LMSpeed currently lists 2 free API providerundefined other undefined} for Gemma 4 31B: Dext API, 91VIP API. Check each provider row before using it because free tier limits can change.