← Compare all APIs

Gemma 4 31B API prices

Compare routes under the same recorded conditions.

Official pricing source ↗

Channel choices

API: google/gemma-4-31b-it · USD · Standard · bf16 · 262K · Global

Reference: 1M input + 1M output tokens; no cache or extras. Not a bill.

Only 1 channel in this scope. Configuration is incomplete; equivalent replacement and savings are unverified.

View recorded configuration conditions

Context limit: 262144

Input/output limits: Unrecorded / 131072

Regions: global

Billing scope: Unrecorded

Parameter declarations: frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Native tool declarations: Source lists no entries

Implicit caching declaration: No

Account restriction: Unrecorded

Subroute label: No extra label

These are recorded source fields; actual capability, performance and account access remain unverified.

Change billing and configuration scope

Novita

novita/bf16

Purchased through OpenRouter

$0.54

1M input + 1M output token subtotal

Input / output per 1M tokens: $0.14 / $0.40

Lowest reference rate in this group; verify output and access.

Use this endpoint
Official API docs ↗

Create a provider API key and set the local environment variable OPENROUTER_API_KEY, then run the example below.

Request URL
https://openrouter.ai/api/v1/chat/completions
Connection settings
Base URL: https://openrouter.ai/api/v1
Catalog model: google/gemma-4-31b-it
Request API model: google/gemma-4-31b-it
Protocol: openai
Provider routing: novita/bf16
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
curl
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": "Read this support ticket and return a JSON object with \"summary\", \"urgency\" (low, medium, or high), and \"next_step\". Use null for missing details.\n\nTicket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo."
    }
  ],
  "provider": {
    "order": [
      "novita/bf16"
    ],
    "only": [
      "novita/bf16"
    ],
    "allow_fallbacks": false,
    "quantizations": [
      "bf16"
    ]
  }
}'
Prompt for your coding agent
Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "google/gemma-4-31b-it". Set provider.only to ["novita/bf16"] and allow_fallbacks to false. Apply the recorded quantization filter. A base slug can match multiple endpoints, so confirm the served route before using the reference price. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-11-22: $0.14 / 1M input tokens, $0.40 / 1M output tokens.  API integration docs: https://openrouter.ai/docs. Billing scope and conditions: Served by Novita through OpenRouter, not a direct-provider contract. Published rates for route novita/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.. Source: https://openrouter.ai/api/v1/models/google/gemma-4-31b-it/endpoints.
Task test prompt
Read this support ticket and return a JSON object with "summary", "urgency" (low, medium, or high), and "next_step". Use null for missing details.

Ticket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo.
Price facts
Input: $0.14 / 1M tokens
Output: $0.40 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-11-22T09:20:23.690Z
Source: https://openrouter.ai/api/v1/models/google/gemma-4-31b-it/endpoints

Source check: 2026-11-22 · valid no later than 2026-11-23 09:21 UTC

Billing evidence and sources

google/gemma-4-31b-it · novita/bf16

Billing conditions

Served by Novita through OpenRouter, not a direct-provider contract. Published rates for route novita/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

Cache read / 1M
Not published
Cache write / 1M
Not published
Per request
Not published
Route
novita/bf16 · bf16

Declared parameters: frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Price source ↗
Compare saved channels →
All quotes, filters and usage tools
History · Billing and conditions

Gemma 4 31B API pricing: official and providers: 16 current published quote records across 2 exact API IDs and 14 providers. Compare API versions, currencies, regions and billing conditions separately; prices do not prove task quality or account access.

Latest recorded source check: 2026-11-22

Recorded changes

Latest 100 recorded price and availability changes
ObservedModel / provider routeChangeInput rateOutput rate

Google: Gemma 4 31B

CoreWeave · coreweave/fp4

Source ↗
Availability

active → unavailable

$0.10 / 1M tokens → $0.10 / 1M tokens$0.34 / 1M tokens → $0.34 / 1M tokens

Google: Gemma 4 31B

PrimeIntellect · primeintellect/fp8

Source ↗
Increase$0.141 / 1M tokens → $0.20 / 1M tokens$0.236 / 1M tokens → $0.335 / 1M tokens

Google: Gemma 4 31B

SambaNova · sambanova

Source ↗
Availability

active → unavailable

$0.38 / 1M tokens → $0.38 / 1M tokens$1.15 / 1M tokens → $1.15 / 1M tokens

Google: Gemma 4 31B

PrimeIntellect · primeintellect/fp8

Source ↗
Decrease$0.20 / 1M tokens → $0.141 / 1M tokens$0.335 / 1M tokens → $0.236 / 1M tokens

Showing up to 100 recent events. Prices for unavailable endpoints are retained for reference. Failed source checks do not establish that a price stayed unchanged.

Open a quote’s billing details for cache reads/writes, request fees and endpoint instructions. Batch, free, promotional and off-peak tiers are selected separately. Context-tier, storage, search, tax and platform fees may be excluded.

Find lower-cost alternatives

Find lower-cost alternatives

Choose your existing model to find lower reference costs with matching declared technical constraints. Output quality remains unverified.

Loading verified quotes…

Users’ choices · Gemma 4 31B

Describe your work to find related tasks.

Public scores by use

The same model scores differently by use. Once you pick a use, the site applies that use’s quality gate before comparing cost.

Text

  • Answer from sources14496118 votes · 2026-11-19
  • Chinese1479521 votes · 2026-11-19
  • Classify14531797 votes · 2026-11-19
  • Extract fields14531797 votes · 2026-11-19
  • General text14526121 votes · 2026-11-19
  • Multi-turn14651121 votes · 2026-11-19
  • Summarize14691798 votes · 2026-11-19
  • Translate & rewrite14383798 votes · 2026-11-19
  • Write1418974 votes · 2026-11-19

Code & tools

  • Code15021408 votes · 2026-11-19
  • Web & frontend137016567 votes · 2026-11-20

Industry

  • Business & finance14491176 votes · 2026-11-19
  • Legal & government1455451 votes · 2026-11-19
  • Medical & health1471421 votes · 2026-11-19

Vision & research

  • Image understanding127942217 votes · 2026-11-19

Scores come from Arena public-preference leaderboards (CC BY 4.0), latest published 2026-11-20. They describe the model, not your task’s success rate or a quantized channel. Arena ↗

View independent evaluation on Artificial Analysis ↗ · external link; we do not copy its scores or prices.

Declared model facts

Declared fields from the OpenRouter model catalog, bound to exact API IDs; not our tests, price approval or account availability.

Input
Image · Text · Video
Output
Text
Context
262K
Reasoning parameter
Supported
Knowledge cutoff
Not declared
Open-weights clue
google/gemma-4-31B-it
Per-API facts · 2 versions
  • google/gemma-4-31b-it · image / text / video → text · 262K · reasoning
  • google/gemma-4-31b-it:free · image / text / video → text · 262K · reasoning

Source: https://openrouter.ai/api/v1/models, captured 2026-11-21T09:20:20.905Z, raw SHA-256: 19214ba490361282… . Unstated facts stay unknown and are not inferred from names or sibling models.

Classification sources

Source declarations for registered versions; not task quality, current account availability or price approval. Unknown versions do not inherit sibling classifications.

Model variants

Snapshots and routing variants remain distinct. Choose an exact ID in the comparison before deciding; model quality and access conditions need your own review.

More from this maker

Google →