> Source page: https://iwkey.com/en/ (Markdown version of this page)

CURATED AI MODEL MARKET

# Specs, pricing, billing — fully transparent

One API key for text and video models, billed by usage.

- [Console](https://iwkey.com/login)
- [Models & pricing](https://iwkey.com/en/models/)

### Model snapshot

On shelf

[All models →](https://iwkey.com/en/models/)

QUICK CONNECT

## Key to first call in three steps

01

#### Create an API key

Sign up in the console to create one; team and project quotas can be provisioned manually.

[Console](https://iwkey.com/login)

02

#### Configure your tool

```
// ~/.claude/settings.json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://iwkey.com",
    "ANTHROPIC_AUTH_TOKEN": "sk-your-key"
  }
}
```

Restart Claude Code after saving

```
# ~/.codex/config.toml
[model_providers.iwkey]
name = "iwkey"
base_url = "https://iwkey.com/v1"
env_key = "IWKEY_KEY"

[profiles.default]
model_provider = "iwkey"
model = "gpt-6-astra"
```

Put your key in the IWKEY_KEY environment variable; fields follow the [docs](https://iwkey.com/en/docs/)

```
# Cherry Studio
Settings → Model services → Add provider
  Type:       OpenAI-compatible
  API base:   https://iwkey.com
  API key:    sk-your-key
Add model → enter the model ID (e.g. claude-opus-5-5)
```

Works for most OpenAI-compatible clients

03

#### Make your first call

```
curl https://iwkey.com/v1/messages \
  -H "x-api-key: $IWKEY_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-opus-5-5",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "..." }]
  }'
```

```
curl https://iwkey.com/v1/chat/completions \
  -H "Authorization: Bearer $IWKEY_KEY" \
  -d '{
    "model": "gpt-6-astra",
    "messages": [{ "role": "user", "content": "..." }]
  }'
```

```
curl https://iwkey.com/videos/v1/videos/generations \
  -H "Authorization: Bearer $IWKEY_KEY" \
  -d '{
    "model": "doubao-seedance-2.0",
    "prompt": "..."
  }'
# async task: submit → poll → download
```

```
curl https://iwkey.com/v1/images/generations \
  -H "Authorization: Bearer $IWKEY_KEY" \
  -d '{
    "model": "gpt-image-2.5-sunburst",
    "prompt": "..."
  }'
```

The live list is the [model market](https://iwkey.com/en/models/) and GET /v1/models

ON THE SHELF

## Frontier models worldwide, pure and authentic

### Text chat

Pay as you go

claude-fable-5-1 1M context 75% off+ $2.50 input /1M $12.50 output /1M $0.0625 cache /1M

claude-opus-5-5 1M context 75% off+ $1.00 input /1M $5.00 output /1M $0.05 cache /1M

gpt-6-astra 1M context 85% off+ $1.50 input /1M $7.50 output /1M $0.15 cache /1M

gpt-6-sol 1M context 85% off+ $0.30 input /1M $1.50 output /1M $0.03 cache /1M

gpt-6-luna 1M context 85% off+ $0.015 input /1M $0.075 output /1M $0.0015 cache /1M

gemini-4-argon 1M context 75% off+ $0.50 input /1M $2.50 output /1M $0.025 cache /1M

### Video generation

Per task · async flow

doubao-seedance-2.0 — Per task duration × resolution Live estimate before submit — cache

doubao-seedance-2.0-fast — Per task duration × resolution Live estimate before submit — cache

doubao-seedance-2.5 — Per task duration × resolution Live estimate before submit — cache

MiniMax-H3 — Per task duration × resolution Live estimate before submit — cache

[All models with live pricing →](https://iwkey.com/en/models/) This page shows a selection of available models; the full list is GET /v1/models. Cache price applies to prompt-cache hits.

Listing changelog

## Recently listed models

2026-10 **gemini-4-argon** Gemini 4 Argon — Google flagship reasoning model, 1M context, 25% of list price

2026-10 **claude-haiku-5-5** Claude Haiku 5.5 — the fastest Claude, 1M context, 25% of list price

2026-09 **gpt-6.1-sol** GPT-6.1 Sol — the new mainstream tier, 1M context, 15% of list price

2026-09 **claude-sonnet-5-5** Claude Sonnet 5.5 — 1M context, 25% of list price

2026-09 **claude-opus-5-5** Anthropic’s new-generation Opus — 1M context, 25% of list price

2026-09 **gpt-6-astra** GPT-6 flagship tier — 1M context, 15% of list price

2026-09 **gpt-6-sol / gpt-6-luna** GPT-6 mainstream and lightweight tiers — 15% of list price; Luna suits batch workloads

2026-09 **claude-fable-5-1** Claude Fable 5.1 — 1M context, thinking supported, 25% of list price

2026-08 **MiniMax-H3** MiniMax video model — billed per task, with a price estimate before you submit

2026-08 **doubao-seedance-2.5 / doubao-seedance-2.0 / doubao-seedance-2.0-fast** ByteDance Seedance video — billed by duration × resolution

FAQ

## Before you start, you might ask

**How do I get started**

Sign up in the console, create an API key, and configure your tool per Quick Connect above. Pay as you go — no monthly fee, no minimum spend.

**Which protocols are supported**

Three endpoints: Anthropic-native /v1/messages, OpenAI-compatible /v1/chat/completions, and async video /videos/v1. The live list is GET /v1/models; full parameters in the [docs](https://iwkey.com/en/docs/).

**Teams and businesses**

We provision team, project, and per-seat quotas manually, with reconciliation and invoicing workflows for small and medium B2B. Email us or reach out in the console.

**How is pricing set**

Discounts are stated against official list price, itemized across input, output, and cache. Market-page prices match actual billing; the console at order time is authoritative.

**Do you store my request content**

Successful text requests store no prompts or completions — only billing metadata such as token counts, timestamps, and model IDs. Video jobs temporarily store parameters and download links for polling. Our billing and logging schema is published on the [transparency page](https://iwkey.com/en/transparency/) — open it and see what we store — and every call is queryable by model, key, and time.

Question not covered? Email support@iwkey.com, or head into the [console](https://iwkey.com/login) and start.