InferIndex
Language, English, EN
Account

ModelsGoogleGemma 4 31B

Gemma 4 31B

google/gemma-4-31b-it Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.205
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.922
Offers
85
Providers
45

Cheapest right now

Consensusprotocol

via LLM Gateway

$0.138 blended / 1M tokens

No change7D
in
$0.10
out
$0.25
Cached input
$0.01

Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

Gemma 4 31B costs from $0.138 per million tokens (at a 3:1 input:output mix): the cheapest of 30 comparable offers, at Consensusprotocol, checked on ; 85 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (55)

  • $0.125 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.15 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.15 · Ranoai via LLM Gateway · cannot be designated the cheapest
  • $0.153 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.153 · Martian via Martian · cannot be designated the cheapest
  • $0.16 · CoreWeave via Kilo Gateway · cannot be designated the cheapest
  • $0.16 · Glama via Glama · cannot be designated the cheapest
  • $0.18 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.18 · Venice via OpenRouter · another route of the same provider
  • $0.183 · Chutes via Kilo Gateway · cannot be designated the cheapest
  • $0.193 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.205 · Crusoe via Kilo Gateway · cannot be designated the cheapest
  • $0.205 · DekaLLM via Kilo Gateway · cannot be designated the cheapest
  • $0.205 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.205 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.205 · Friendli via Kilo Gateway · cannot be designated the cheapest
  • $0.205 · Friendli via Vercel AI Gateway · another route of the same provider
  • $0.205 · Novita via Hugging Face · another route of the same provider
  • $0.205 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.205 · Novita via LLM API · cannot be designated the cheapest
  • $0.205 · Novita via Vercel AI Gateway · another route of the same provider
  • $0.205 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
  • $0.205 · Novita via LLM Gateway · another route of the same provider
  • $0.205 · Friendli via OpenRouter · another route of the same provider
  • $0.205 · Novita via OpenRouter · another route of the same provider
  • $0.213 · Parasail via Kilo Gateway · cannot be designated the cheapest
  • $0.213 · Parasail via OpenRouter · another route of the same provider
  • $0.216 · Greenference via Eden AI · cannot be designated the cheapest
  • $0.225 · FPT AI Factory · cannot be designated the cheapest
  • $0.229 · DeepInfra · priority tier
  • $0.229 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.229 · DeepInfra via OpenRouter · another route of the same provider
  • $0.23 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.25 · DeepInfra · another route of the same provider
  • $0.25 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.25 · DeepInfra via Hugging Face · another route of the same provider
  • $0.25 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.25 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.25 · DeepInfra via LLM Gateway · another route of the same provider
  • $0.25 · DeepInfra via OpenRouter · another route of the same provider
  • $0.265 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.275 · ai& · cannot be designated the cheapest
  • $0.279 · Infomaniak via Eden AI · cannot be designated the cheapest
  • $0.375 · DeepInfra · priority tier
  • $0.375 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.375 · DeepInfra via OpenRouter · priority tier
  • $0.405 · io.net · cannot be designated the cheapest
  • $0.45 · Sail Research via Requesty · another route of the same provider
  • $0.535 · Together via LLM Gateway · cannot be designated the cheapest
  • $0.573 · Io Net via Kilo Gateway · cannot be designated the cheapest
  • $0.573 · SambaNova via Kilo Gateway · cannot be designated the cheapest
  • $0.573 · SambaNova via OpenRouter · another route of the same provider
  • $0.813 · ModelRun via Kilo Gateway · cannot be designated the cheapest
  • $0.813 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $1.12 · Cerebras via LLM Gateway · cannot be designated the cheapest

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

DeepInfra

directYou buy access straight from the company that runs the model on its servers. · fp4 · 262k

$0.153 blended / 1M tokens

in
$0.09
out
$0.34
Cached input
$0.05
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.138, Consensusprotocol–
2026-10-03$0.064, Greenference–
2026-10-04$0.138, Consensusprotocol–
2026-10-05$0.138, Consensusprotocol–
2026-10-06$0.076, Greenference–
2026-10-07$0.138, Consensusprotocol–
2026-10-08$0.076, Greenference–
2026-10-09$0.138, Consensusprotocol–
2026-10-10$0.138, Consensusprotocol–
2026-10-11$0.138, Consensusprotocol–
2026-10-12$0.138, Consensusprotocol–
2026-10-13$0.138, Consensusprotocol–
2026-10-14$0.138, Consensusprotocol–
2026-10-15$0.138, Consensusprotocol–
2026-10-16$0.138, Consensusprotocol–
2026-10-17$0.138, Consensusprotocol–
2026-10-18$0.138, Consensusprotocol–
2026-10-19$0.138, Consensusprotocol–
2026-10-20$0.138, Consensusprotocol–
2026-10-21$0.138, Consensusprotocol–
2026-10-22$0.138, Consensusprotocol–
2026-10-23$0.138, Consensusprotocol–
2026-10-24$0.138, Consensusprotocol–
2026-10-25$0.138, Consensusprotocol–
2026-10-26$0.138, Consensusprotocol–
2026-10-27$0.138, Consensusprotocol–
2026-10-28$0.138, Consensusprotocol–
2026-10-29$0.138, Consensusprotocol–
2026-10-30$0.138, Consensusprotocol–
2026-10-31$0.138, Consensusprotocol–

Cheapest offer

Offers

The 25 cheapest of 85 offers

Offers for Gemma 4 31B, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 Arkanecloudvia Eden AI 0.10  0.20  0.125 – 131k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
2 Consensusprotocolvia LLM Gateway 0.10  0.25  0.138 – – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
3 FastRouter 0.10  0.30  0.15  – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at FastRouter (opens in a new tab)
4 Ranoaivia LLM Gateway 0.10  0.30  0.15  – – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
5 Runwarevia LLM Gateway 0.102 0.297 0.151 – – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
6 DeepInfra 0.09  0.34  0.153 fp4 262k United States
Go to offer at DeepInfra (opens in a new tab)
7 DeepInfravia Eden AI 0.09  0.34  0.153 fp4 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
8 Martian 0.09  0.34  0.153 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
9 CoreWeavevia Kilo Gateway 0.10  0.34  0.16  fp4 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
10 Glama 0.10  0.34  0.16  – 262k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
11 NanoGPT 0.10  0.34  0.16  – 262k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
12 CoreWeavevia OpenRouter 0.10  0.34  0.16  fp4 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
13 Venice 0.12  0.36  0.18  fp4 256k
Go to offer at Venice (opens in a new tab)
14 Featherless 0.12  0.36  0.18  – 33k
Go to offer at Featherless (opens in a new tab)
15 Venicevia Kilo Gateway 0.12  0.36  0.18  fp4 256k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
16 Venicevia OpenRouter 0.12  0.36  0.18  fp4 256k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
17 Chutesvia Kilo Gateway 0.12  0.37  0.183 fp4 131k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
18 Chutesvia OpenRouter 0.12  0.37  0.183 fp4 131k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
19 OrcaRouter 0.13  0.38  0.193 – – Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at OrcaRouter (opens in a new tab)
20 DeepInfravia Requesty 0.13  0.38  0.193 fp8 262k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
21 NanoGPT 0.14  0.40  0.205 – 262k
Go to offer at NanoGPT (opens in a new tab)
22 Friendli 0.14  0.40  0.205 – 262k
See pricing at Friendli (opens in a new tab)
23 Novita 0.14  0.40  0.205 bf16 262k
See pricing at Novita (opens in a new tab)
24 Crusoevia Kilo Gateway 0.14  0.40  0.205 bf16 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
25 DekaLLMvia Kilo Gateway 0.14  0.40  0.205 – 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

Show all 85 offers

5 flex or batch offers hidden (lower priority, variable latency).

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Consensusprotocol$9.75per month
  2. DeepInfra$10.50per month+$0.75 vs the cheapest
  3. NanoGPT$11.10per month+$1.35 vs the cheapest

Host it yourself instead? See the break-even

Compare Gemma 4 31B with

Related models

More from Google

All Google models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=google/gemma-4-31b-it
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.