We saw very high sudden increase in usage dollars because of low supply on codebuddy, please adjust your budget accordingly.·
We saw very high sudden increase in usage dollars because of low supply on codebuddy, please adjust your budget accordingly.·
InferHub
FeaturesPricingIntegrationDocs
Live market
ag/claude-opus-4-6-thinkingask$0.02last$0.303
ag/claude-sonnet-4-6ask$0.006last$0.0067
ag/gemini-3.6-flash-highask$0.0008last$0.0043
ag/gemini-3.7-flash-highask$0.0008last$0.0001
ag/gemini-3.8-flash-highask$0.0008last$0.0041
ag/gemini-pro-agentask$0.002last$0.034
ali/deepseek-v4-flash-0731ask$0.0062last$0.0007
ali/deepseek-v4-pro-0813ask$0.0046last$0.0047
ali/glm-5.2ask$0.0112last$0.0113
ali/kimi-k2.7-codeask$0.0009last$0.4348
ali/kimi-k3ask$0.111last$0.013
ali/qwen3.8-maxask$0.002last$0.0009
cb/claude-opus-4.6ask$0.44last$0.0125
cb/claude-opus-4.7-1mask$0.44last$0.0089
cb/claude-opus-5ask$0.44last$0.3913
cb/deepseek-v4.1-flashask$0.0075last$0.0027
cb/gemini-2.5-flash-imageask$0.0267last$0.0509
cb/gemini-3.0-pro-imageask$0.178last$1.132
cb/gemini-3.1-flash-imageask$0.0445last$0.4757
cb/gemini-3.1-proask$0.178last$0.3871
cb/glm-5.2ask$0.1246last$0.3103
cb/glm-5.3ask$0.1246last$0.0015
cb/gpt-5.3-codexask$0.1557last$0
cb/gpt-5.4ask$0.2225last$1.25
cb/gpt-5.5ask$0.44last$2
cb/gpt-5.6-lunaask$0.0178last$0.0412
cb/gpt-5.6-solask$0.09last$0.0118
cb/gpt-5.6-terraask$0.178last$1.4286
cb/gpt-6-astraask$0.27last$0.0383
cb/gpt-image-2ask$0.712last$2.613
cb/kimi-k3ask$0.267last$0.6887
cb/minimax-m3ask$0.0267last$0.0617
cbcn/deepseek-v4-flashask$0.0031last$0.004
cbcn/deepseek-v4-proask$0.0092last$0.002
cbcn/deepseek-v4.1-flashask$0.0021last$0.0003
cbcn/glm-5.2ask$0.0196last$0.2381
cbcn/glm-5.3ask$0.0196last$0.0035
cbcn/glm-5.3-flashask$0.0021last$0.0015
cbcn/kimi-k2.6ask$0.0133last$0.0535
cbcn/kimi-k2.7ask$0.0133last$0.0017
cbcn/kimi-k3ask$0.042last$0.0369
cbcn/minimax-m2.7ask$0.0042last$1.25
cbcn/minimax-m3ask$0.0042last$0.0044
cc/claude-fable-5ask$1last$4.1579
cc/claude-fable-5-1ask$1last$1.7619
cc/claude-haiku-4-5ask$0.1last$0.3111
cc/claude-opus-4-6ask$0.5last$0.7411
cc/claude-opus-4-7ask$0.5last$0.5119
cc/claude-opus-4-8ask$0.5last$0.7671
cc/claude-opus-5ask$0.5last$0.796
cc/claude-sonnet-4-5ask$0.3last$1.1094
cc/claude-sonnet-4-6ask$0.3last$2.9269
cc/claude-sonnet-5ask$0.3last$1.0455
cmc/MiniMaxAI/MiniMax-M2.5ask$0.03last$0.4762
cmc/MiniMaxAI/MiniMax-M2.7ask$0.03last—
cmc/Qwen/Qwen3.6-Max-Previewask$0.13last$0.4375
cmc/deepseek/deepseek-v4-flashask$0.015last$0.0151
cmc/deepseek/deepseek-v4-proask$0.064last$0.1682
cmc/meta/muse-spark-1.2-contributorask$0.01last$0.0131
cmc/meta/muse-spark-1.3-contributorask$0.01last$0.0101
cmc/moonshotai/Kimi-K2.6ask$0.095last$0.2778
cmc/moonshotai/Kimi-K2.7-Codeask$0.095last$0.2537
cmc/moonshotai/Kimi-K3ask$0.294last$0.5385
cmc/xai/grok-4.5ask$0.2last$0.3333
cmc/xai/grok-4.6ask$0.64last$1.6571
cmc/z-ai/glm-5.3-flashask$0.0144last$0.0162
cmc/zai-org/GLM-5.1ask$0.14last$0.5
cmc/zai-org/GLM-5.2ask$0.1386last$0.3846
cp/cline-pass/deepseek-v4-flashask$0.0814last$0.229
cp/cline-pass/deepseek-v4-proask$0.031last$0.3971
cp/cline-pass/glm-5.2ask$0.0658last$0.7647
cp/cline-pass/glm-5.3ask$0.42last$0.5556
cp/cline-pass/kimi-k2.6ask$0.285last$0.3517
cp/cline-pass/kimi-k2.7-codeask$0.0095last$0.6667
cp/cline-pass/kimi-k3ask$1.089last$1.6838
cp/cline-pass/mimo-v2.5ask$0.0525last$0.0262
cp/cline-pass/mimo-v2.5-proask$0.6525last$0.0717
cp/cline-pass/minimax-m3ask$0.1125last$0.2787
cp/cline-pass/qwen3.7-maxask$0.1128last$3.2952
cp/cline-pass/qwen3.7-plusask$0.18last—
cp/cline-pass/qwen3.8-maxask$0.094last$0.122
cp/xai/grok-4.5ask$0.094last$0.0617
cp/xai/grok-4.6ask$0.094last$0.083
cp/zai/glm-5.3-flashask$0.0057last$0.0069
cx/gpt-5.5ask$0.095last$0.4667
cx/gpt-5.6-lunaask$0.0038last$0.0006
cx/gpt-5.6-solask$0.145last$0.2256
cx/gpt-5.6-terraask$0.048last$0
cx/gpt-6-astraask$0.29last$0.2257
ocg/deepseek-v4-flashask$0.0312last$0.0035
ocg/glm-5.1ask$0.1988last$0.5882
ocg/glm-5.2ask$0.1988last—
ocg/glm-5.3ask$0.1988last$0.0252
ocg/glm-5.3-flashask$0.0213last$0.0334
ocg/gpt-5.6-lunaask$0.0284last$0
ocg/grok-4.5ask$0.284last—
ocg/kimi-k2.6ask$0.1349last$0.1203
ocg/kimi-k2.7-codeask$0.1349last$0.1763
ocg/kimi-k3ask$0.426last$1.0618
ocg/mimo-v2.5ask$0.0199last$0.0402
ocg/mimo-v2.5-proask$0.0618last$0.0391
ocg/minimax-m2.5ask$0.0426last$0.1414
ocg/minimax-m2.7ask$0.0426last$0.1172
ocg/minimax-m3ask$0.0426last$0.0459
ocg/qwen3.7-plusask$0.1704last$0.6498
ocg/qwen3.8-maxask$0.284last—
zai/glm-4.6vask$0.0003last$1.25
zai/glm-4.7ask$0.0006last$0.0789
zai/glm-5ask$0.001last$0.7143
zai/glm-5-turboask$0.0012last$0.7143
zai/glm-5.1ask$0.0014last$0.7143
zai/glm-5.2ask$0.0014last$0.7143
zai/glm-5.3ask$0.0014last$0.0739
zai/glm-5.3-flashask$0.0001last$0.0001
ag/claude-opus-4-6-thinkingask$0.02last$0.303
ag/claude-sonnet-4-6ask$0.006last$0.0067
ag/gemini-3.6-flash-highask$0.0008last$0.0043
ag/gemini-3.7-flash-highask$0.0008last$0.0001
ag/gemini-3.8-flash-highask$0.0008last$0.0041
ag/gemini-pro-agentask$0.002last$0.034
ali/deepseek-v4-flash-0731ask$0.0062last$0.0007
ali/deepseek-v4-pro-0813ask$0.0046last$0.0047
ali/glm-5.2ask$0.0112last$0.0113
ali/kimi-k2.7-codeask$0.0009last$0.4348
ali/kimi-k3ask$0.111last$0.013
ali/qwen3.8-maxask$0.002last$0.0009
cb/claude-opus-4.6ask$0.44last$0.0125
cb/claude-opus-4.7-1mask$0.44last$0.0089
cb/claude-opus-5ask$0.44last$0.3913
cb/deepseek-v4.1-flashask$0.0075last$0.0027
cb/gemini-2.5-flash-imageask$0.0267last$0.0509
cb/gemini-3.0-pro-imageask$0.178last$1.132
cb/gemini-3.1-flash-imageask$0.0445last$0.4757
cb/gemini-3.1-proask$0.178last$0.3871
cb/glm-5.2ask$0.1246last$0.3103
cb/glm-5.3ask$0.1246last$0.0015
cb/gpt-5.3-codexask$0.1557last$0
cb/gpt-5.4ask$0.2225last$1.25
cb/gpt-5.5ask$0.44last$2
cb/gpt-5.6-lunaask$0.0178last$0.0412
cb/gpt-5.6-solask$0.09last$0.0118
cb/gpt-5.6-terraask$0.178last$1.4286
cb/gpt-6-astraask$0.27last$0.0383
cb/gpt-image-2ask$0.712last$2.613
cb/kimi-k3ask$0.267last$0.6887
cb/minimax-m3ask$0.0267last$0.0617
cbcn/deepseek-v4-flashask$0.0031last$0.004
cbcn/deepseek-v4-proask$0.0092last$0.002
cbcn/deepseek-v4.1-flashask$0.0021last$0.0003
cbcn/glm-5.2ask$0.0196last$0.2381
cbcn/glm-5.3ask$0.0196last$0.0035
cbcn/glm-5.3-flashask$0.0021last$0.0015
cbcn/kimi-k2.6ask$0.0133last$0.0535
cbcn/kimi-k2.7ask$0.0133last$0.0017
cbcn/kimi-k3ask$0.042last$0.0369
cbcn/minimax-m2.7ask$0.0042last$1.25
cbcn/minimax-m3ask$0.0042last$0.0044
cc/claude-fable-5ask$1last$4.1579
cc/claude-fable-5-1ask$1last$1.7619
cc/claude-haiku-4-5ask$0.1last$0.3111
cc/claude-opus-4-6ask$0.5last$0.7411
cc/claude-opus-4-7ask$0.5last$0.5119
cc/claude-opus-4-8ask$0.5last$0.7671
cc/claude-opus-5ask$0.5last$0.796
cc/claude-sonnet-4-5ask$0.3last$1.1094
cc/claude-sonnet-4-6ask$0.3last$2.9269
cc/claude-sonnet-5ask$0.3last$1.0455
cmc/MiniMaxAI/MiniMax-M2.5ask$0.03last$0.4762
cmc/MiniMaxAI/MiniMax-M2.7ask$0.03last—
cmc/Qwen/Qwen3.6-Max-Previewask$0.13last$0.4375
cmc/deepseek/deepseek-v4-flashask$0.015last$0.0151
cmc/deepseek/deepseek-v4-proask$0.064last$0.1682
cmc/meta/muse-spark-1.2-contributorask$0.01last$0.0131
cmc/meta/muse-spark-1.3-contributorask$0.01last$0.0101
cmc/moonshotai/Kimi-K2.6ask$0.095last$0.2778
cmc/moonshotai/Kimi-K2.7-Codeask$0.095last$0.2537
cmc/moonshotai/Kimi-K3ask$0.294last$0.5385
cmc/xai/grok-4.5ask$0.2last$0.3333
cmc/xai/grok-4.6ask$0.64last$1.6571
cmc/z-ai/glm-5.3-flashask$0.0144last$0.0162
cmc/zai-org/GLM-5.1ask$0.14last$0.5
cmc/zai-org/GLM-5.2ask$0.1386last$0.3846
cp/cline-pass/deepseek-v4-flashask$0.0814last$0.229
cp/cline-pass/deepseek-v4-proask$0.031last$0.3971
cp/cline-pass/glm-5.2ask$0.0658last$0.7647
cp/cline-pass/glm-5.3ask$0.42last$0.5556
cp/cline-pass/kimi-k2.6ask$0.285last$0.3517
cp/cline-pass/kimi-k2.7-codeask$0.0095last$0.6667
cp/cline-pass/kimi-k3ask$1.089last$1.6838
cp/cline-pass/mimo-v2.5ask$0.0525last$0.0262
cp/cline-pass/mimo-v2.5-proask$0.6525last$0.0717
cp/cline-pass/minimax-m3ask$0.1125last$0.2787
cp/cline-pass/qwen3.7-maxask$0.1128last$3.2952
cp/cline-pass/qwen3.7-plusask$0.18last—
cp/cline-pass/qwen3.8-maxask$0.094last$0.122
cp/xai/grok-4.5ask$0.094last$0.0617
cp/xai/grok-4.6ask$0.094last$0.083
cp/zai/glm-5.3-flashask$0.0057last$0.0069
cx/gpt-5.5ask$0.095last$0.4667
cx/gpt-5.6-lunaask$0.0038last$0.0006
cx/gpt-5.6-solask$0.145last$0.2256
cx/gpt-5.6-terraask$0.048last$0
cx/gpt-6-astraask$0.29last$0.2257
ocg/deepseek-v4-flashask$0.0312last$0.0035
ocg/glm-5.1ask$0.1988last$0.5882
ocg/glm-5.2ask$0.1988last—
ocg/glm-5.3ask$0.1988last$0.0252
ocg/glm-5.3-flashask$0.0213last$0.0334
ocg/gpt-5.6-lunaask$0.0284last$0
ocg/grok-4.5ask$0.284last—
ocg/kimi-k2.6ask$0.1349last$0.1203
ocg/kimi-k2.7-codeask$0.1349last$0.1763
ocg/kimi-k3ask$0.426last$1.0618
ocg/mimo-v2.5ask$0.0199last$0.0402
ocg/mimo-v2.5-proask$0.0618last$0.0391
ocg/minimax-m2.5ask$0.0426last$0.1414
ocg/minimax-m2.7ask$0.0426last$0.1172
ocg/minimax-m3ask$0.0426last$0.0459
ocg/qwen3.7-plusask$0.1704last$0.6498
ocg/qwen3.8-maxask$0.284last—
zai/glm-4.6vask$0.0003last$1.25
zai/glm-4.7ask$0.0006last$0.0789
zai/glm-5ask$0.001last$0.7143
zai/glm-5-turboask$0.0012last$0.7143
zai/glm-5.1ask$0.0014last$0.7143
zai/glm-5.2ask$0.0014last$0.7143
zai/glm-5.3ask$0.0014last$0.0739
zai/glm-5.3-flashask$0.0001last$0.0001
InferHub — the AI inference marketplace

Maximize every token you spend on AI.

Call dozens of frontier models through one OpenAI- and Anthropic-compatible API, billed per million tokens in USDC and routed to the best-priced healthy provider. No monthly plan, no commitment — pay for what you use, at a fraction of official pricing.

💰$1321759.70 saved by users vs official pricing
I want API access

Pay per token. Maximum value.

Top up USDC, grab one key, then npx @inferhub/helper — or call any model from your SDK. Stop calling, stop paying.

99.8Mtotal requests
3820517.7Mtokens routed

Top 5 consumer spending

All time
1a63343940d7c
$12430 USDC
a63343940d7c · $12430.207996 USDC
2c136d3271380
$4316 USDC
c136d3271380 · $4315.620027 USDC
31430c0bb15f7
$1043 USDC
1430c0bb15f7 · $1042.571871 USDC
4e8290fda427c
$919 USDC
e8290fda427c · $918.980453 USDC
5b9e6f45a3b88
$784 USDC
b9e6f45a3b88 · $784.182513 USDC
I have capacity

Turn idle capacity into USDC.

Connect one of the curated upstreams — Claude, Codex, z.ai, OpenCode Go, Command Code — and earn on the headroom you don't use.

$5720.36ready to spend
$23826.17paid to publishers

Top 5 publisher earnings

All time
13012952611b7
$2087 USDC
3012952611b7 · $2087.09659 USDC
265457f30696c
$1778 USDC
65457f30696c · $1778.348962 USDC
36b652a8e5328
$1671 USDC
6b652a8e5328 · $1671.076729 USDC
4569edb1ca39b
$1567 USDC
569edb1ca39b · $1566.975621 USDC
583b9009087d9
$1058 USDC
83b9009087d9 · $1057.719494 USDC
50% off official pricing — or more USDC on Solana mainnet OpenAI + Anthropic compatible

Reach upstreams that normally live behind a monthly plan

ClaudeAnthropic-compatible
CodexOpenAI-compatible
z.ai GLMOpenAI-compatible
OpenCode GoOpenAI-compatible
Command CodeAI SDK compatible

One API, two protocols, a marketplace behind it

InferHub is an OpenAI- and Anthropic-compatible API with a marketplace behind it. Call any model with one key; route to capacity that fits your budget.

One key, both protocols

Hit /v1/chat/completions or /v1/messages with a single InferHub API key. Or run npx @inferhub/helper to wire Claude Code, Codex, OpenCode, and more in seconds.

Combos: one name, many upstreams

combo/<slug> virtual models check your budget, then route to the first provider with available capacity. One model name, automatic failover, no manual re-rolls.

Real upstream quota tracking

We poll Claude, Codex, and z.ai for live 5-hour and weekly usage windows. No manual caps — exhaustion is detected from the source of truth, so your provider never cuts you off without warning.

Pay-per-use in USDC

Tokens are metered per million and deducted from your balance in real time. Stop calling, stop paying. No subscription to cancel. USDC on Solana mainnet.

Credentials encrypted at rest

Every provider key is encrypted at rest and injected only at the wire — we never expose your raw credential. Release control and rotation anytime.

Per-provider proxy pool

Each publisher's outbound traffic rides a least-used proxy from its configured pool, keeping upstream fingerprints stable and traffic distributed.

Get started in one command

Coding agents first: run the helper, paste your key, pick models. Or point your OpenAI / Anthropic SDK at InferHub — same request shape, same streaming, one key for both.

Coding agents
Claude Code · Codex · OpenCode · Hermes · OpenClaw · Cline
# Point Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cline at InferHub
npx @inferhub/helper

# Interactive wizard:
#  1. paste API key  → validated via GET /v1/models
#  2. select agents
#  3. search & pick models
#  4. confirm → configs written
OpenAI SDK
Chat completions, streaming, tool calls
// OpenAI SDK → any upstream
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.INFERHUB_KEY,
  baseURL: "https://api.inferhub.dev/v1",
});

const res = await client.chat.completions.create({
  model: "claude/sonnet-4-5",
  messages: [{ role: "user", content: "Explain PKCE." }],
});
Anthropic SDK
Messages API, native Claude
// Anthropic SDK → Claude upstream
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.INFERHUB_KEY,
  baseURL: "https://api.inferhub.dev",
});

const res = await client.messages.create({
  model: "claude/opus-4-8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a haiku." }],
});
Consumer combos
Route to the best provider within budget
// Consumer combo → first provider with capacity
const res = await client.chat.completions.create({
  model: "combo/code-assistant",
  messages: [{ role: "user", content: "Refactor this function." }],
  stream: true,
});

Full walkthrough in docs. Package: @inferhub/helper.

Models reachable without buying the plan

Per-Mtoken pricing in USDC — guaranteed at or below 50% of official rates. Publishers set their ask; the platform enforces the cap.

Free models are listed as free/<provider>/<model> and settle at $0, but only accounts with balance > 0 can call them. Free capacity is best-effort and can be unavailable or stopped at any time.

ModelFamilyInput / MtokOutput / Mtok
ag/claude-opus-4-6-thinkingAntigravity$0.02$0.1
ag/claude-sonnet-4-6Antigravity$0.006$0.03
ag/gemini-3.6-flash-highAntigravity$0.00075$0.00375
ag/gemini-3.7-flash-highAntigravity$0.00075$0.00375
ag/gemini-3.8-flash-highAntigravity$0.00075$0.00375
ag/gemini-pro-agentAntigravity$0.002$0.012
cc/claude-fable-5Claude Code$1$5
cc/claude-fable-5-1Claude Code$1$5
cc/claude-haiku-4-5Claude Code$0.1$0.5
cc/claude-opus-4-6Claude Code$0.5$2.5
cc/claude-opus-4-7Claude Code$0.5$2.5
cc/claude-opus-4-8Claude Code$0.5$2.5

Two paths, same platform

01
Pick your path

Land on the consumer path to call models on pay-per-use, or the publisher path to share capacity and earn.

02
Consumer: deposit and call

Deposit USDC, generate one API key, and call any model through /v1/chat/completions or /v1/messages. Optionally attach a bid with x-max-input-price / x-max-output-price and we route to a provider that meets it.

03
Publisher: connect and price

Pick a curated upstream — Claude, Codex, z.ai, OpenCode Go, or Command Code — connect its key, set your per-Mtoken ask, and your capacity joins the pool.

04
Meter and settle

Tokens are metered per million and deducted from the consumer balance in real time. Publishers see earnings accrue and withdraw to Solana mainnet once they clear the 5 USDC minimum. Stop calling, stop paying.

For publishers

Put your model capacity to work

Your idle model capacity has headroom. Connect one of the curated upstreams once, set your per-Mtoken price, and earn USDC from capacity you'd otherwise waste. We track real upstream usage so you never get cut off unexpectedly.

  • Credentials encrypted at rest — we never expose your raw key.
  • Upstreams connect with a scoped API key — no other privileges required.
  • Live 5-hour and weekly quota monitoring protects your account from surprise exhaustion.
  • Per-provider outbound proxy pool routes your traffic through least-used egress.
  • Instant USDC settlement on Solana mainnet; withdraw at the 5 USDC minimum.
Publisher dashboard
Connected capacityClaude · Codex · z.ai
Your ask$0.40 / Mtok in
Quota health5h: 38% · weekly: 21%
Earnings (this period)128.40 USDC
Available to withdraw≥ 5 USDC → Solana

Pay-per-use for consumers, payout for publishers

Consumers optionally attach a bid (x-max-input-price / x-max-output-price) and we route to a provider that meets it. Skip the bid and we route to the first provider with capacity within your budget. No subscription tier required on either side.

Consumer
Per million tokens, in USDC
  • ✓One key for OpenAI- and Anthropic-compatible endpoints
  • ✓combo/<slug> routing across providers, budget-aware
  • ✓Real-time balance deduction — stop calling, stop paying
  • ✓Optional bid headers to cap your per-Mtoken spend
Publisher
You set the per-Mtoken ask
  • ✓Curated upstreams: Claude, Codex, z.ai, OpenCode Go, Command Code
  • ✓Live 5h and weekly quota windows tracked for you
  • ✓Earnings accrue per settled request, withdrawable at 5 USDC
  • ✓Per-provider proxy pool keeps your upstream stable
Platform
20% platform fee
  • ✓Flat 20% of each settled consumer charge
  • ✓No listing fee, no monthly publisher subscription
  • ✓USDC settlement on Solana mainnet
  • ✓Quota polling, routing, and metering handled by the proxy

Call models now, or let yours earn

Deposit USDC and hit your first model in minutes — or connect a curated upstream and start earning from idle capacity. Both paths run on the same OpenAI- and Anthropic-compatible API, settled in USDC on Solana mainnet.

Join the InferHub community on Discord

Get support, request features, share suggestions, and follow updates. Whether you're calling models or publishing capacity, we're most responsive there.

Join the Discord
InferHub

Pay once. Use everywhere. A per-token marketplace for AI inference, settled in USDC on Solana.

Product
  • Pricing & models
  • Integration & API
  • Documentation
  • Features
  • For publishers
Account
  • Sign in
  • Sign up
Legal
  • Privacy Policy
  • Terms of Service
  • Refund Policy
Support
  • FAQ
  • Contact
  • Status

© 2026 InferHub · PT. Lancar Dalam Harapan. All rights reserved.

Discord

Built for the open AI ecosystem.