Infero
Log inStart free

Open-weight models. One honest price.

DeepSeek, Qwen, Kimi, and GLM behind one OpenAI- and Anthropic-compatible key, priced at the cheapest floor plus 6%.

Start freeRead the docs
Live prices, per 1M tokensprovider floor first
deepseek-v4-flash$0.09 / $0.18$0.10 / $0.19
deepseek-v4-pro$1.60 / $3.20$1.70 / $3.39
qwen3-235b$0.09 / $0.55$0.10 / $0.58
qwen3.5-397b$0.45 / $3.00$0.48 / $3.18
qwen3-max$1.20 / $6.00$1.27 / $6.36
View the full board
10.9x

price spread for the same open model across providers

37 to 93%

benchmark score of identical weights, depending on who serves them

27 models

curated open-weight catalog across four providers, behind one key

What honest means here

Every claim below has a public endpoint behind it. These panels are reading them right now, failures included.

Verified serving

The same weights differ by host, so canaries test tool calling, code generation, and unicode on every route. A route that fails never serves your tool calls.

0 of 0 models pass every canary over the last 7 days

Full scorecard

Failover you never notice

Requests go to the cheapest healthy provider. When one degrades, the next one answers and you never see it.

Measured over the last 24 hours

deepinfra85.1%3162ms
venice0.0%n/a

Tracker pricing

Every sticker is the cheapest provider floor plus 6%. Prices only ever move down automatically, and a mid-month cut re-rates your whole month as a rebate.

Price history

27 stickers tracked since Aug 21, no provider cut has landed yet. When one does, the sticker follows on the watcher's next pass and the month is re-rated.

Drop-in by design

Works with any OpenAI or Anthropic SDK and the agents built on them: Claude Code, Codex, Cline, OpenCode. Point the base URL at Infero and keep everything else.

# or ANTHROPIC_BASE_URL for Claude Code
export OPENAI_BASE_URL=https://api.infero.xyz/v1
export OPENAI_API_KEY=sk-infero-...

Fair with money

Prepaid only

You can never spend money that does not exist.

Credits never expire

No use-it-or-lose-it clauses on your balance.

1:1 crypto top-ups

On Base, at the signed rate. Pay in ELSA and get 5% extra credit, up to $25 per account.

USDCELSA+5% extra credit, up to $25 per account

Per-key budgets

Caps and model allowlists give a leaked key a blast radius.

Questions

What is Infero?
An inference gateway for open-weight models such as DeepSeek, Qwen, Kimi and GLM. One API key, compatible with the OpenAI and Anthropic SDKs, routed across several upstream providers with automatic failover.
How is pricing set?
Every model's price is the cheapest provider floor plus 6%, per million tokens. Prices only move down automatically: when a provider cuts its price the sticker follows, and the cut re-rates your current month as a rebate. The full price history is public.
What does verified serving mean?
The same open weights can behave differently depending on who hosts them. Every model and provider pair is tested with canaries for tool-call conformance, code generation and unicode round-trips. Scores are public, and requests that use tools never route to an endpoint failing the tool-call canary.
How do I pay?
Prepaid credits that never expire. Signing in creates the account with $0.50 of free credit; top up with USDC or ELSA on Base, credited 1:1 at the signed rate, gasless. Paying in ELSA adds 5% extra credit, up to $25 per account.
Does it work with Claude Code, Codex and other agents?
Yes. Anything that speaks the OpenAI or Anthropic API works by changing the base URL: set OPENAI_BASE_URL or ANTHROPIC_BASE_URL to the gateway and keep the rest of your setup.

Try it on us

$0.50 of free credit on your first sign-in. No card, one account per email.

Start free