GC4.AI
Convert a card
Developers

Change one line.
Keep your code.

The endpoint is OpenAI-compatible: point your existing SDK at api.gc4.ai and your gift-card balance pays for every model.

Email-only account · No credit card · Ever
Get a keyQuickstart
api.gc4.ai
-base_url="https://api.openai.com/v1"+base_url="https://api.gc4.ai/v1"
That's the whole migration. 44 models, one balance,per-token prices mirrored from openrouter.ai.
Quickstart

200 on the first paste.

You just minted a key, so it's inlined here for this session. Pick a tab, paste, run.

quickstart.gc4.ai
1from openai import OpenAI
2 
3client = OpenAI(
4    base_url="https://api.gc4.ai/v1",
5    api_key="gc4-8f2KQmVrTz31uHe6pLaXw41NcB7dGsRtPq0ZkLmJhVx",  # your key, already inlined
6)
7 
8r = client.chat.completions.create(
9    model="anthropic/claude-haiku-4.5",
10    messages=[{"role": "user", "content": "Say hi in 5 words."}],
11)
12print(r.choices[0].message.content)
Expected response
{
  "choices": [{ "message": {
    "role": "assistant",
    "content": "Hi there, five words exactly." } }],
  "usage": { "prompt_tokens": 13, "completion_tokens": 8,
             "cost_usd": 0.000053 }
}
First request detected21 tokens · $0.000053 · ledgered in your account
Errors

Every error you'll meet.

An empty balance is a hard stop: there is no overdraft and no negative balance, ever. Limits are 60 requests a minute per key. Upstream provider errors pass through unchanged in OpenAI-compatible format.

401Bad or revoked key{ "error": { "code": "invalid_key", "message": "Key not recognized. Check for whitespace." } }
404Model id not on the ledger (typo'd slug){ "error": { "code": "model_not_found", "message": "No model anthropic/claude-haiku-45. Did you mean anthropic/claude-haiku-4.5?" } }
402Balance empty: hard stop, never overdraft{ "error": { "code": "balance_empty", "message": "Balance is $0.00. Convert a card at gc4.ai/convert.", "convert_url": "https://gc4.ai/convert" } }
429Rate limited: 60 req/min per key{ "error": { "code": "rate_limited", "message": "60 requests/min exceeded. Retry after 2.1s.", "retry_after": 2.1 } }
Models

The price ledger.

What a card buys$→ ~6.5M tokens → ~7,700 answers on Claude Haiku 4.5
models.gc4.ai
Mirrors openrouter.ai · last synced Jun 9, 2026 14:02 UTC · 44 modelsVerify →
ModelIn $/MOut $/M~Answers/$1
Claude Fable 5anthropic/claude-fable-5$5.00$25.00~62
Claude Opus 4.8anthropic/claude-opus-4-8$12.00$60.00~26
Claude Sonnet 4.6anthropic/claude-sonnet-4-6$2.50$12.50~123
Claude Haiku 4.5anthropic/claude-haiku-4.5$1.00$5.00~308
GPT-5.5openai/gpt-5.5$1.25$10.00~158
GPT-5.5 Miniopenai/gpt-5.5-mini$0.25$2.00~792
o5openai/o5$10.00$40.00~38
GPT-4.1openai/gpt-4.1$2.00$8.00~189
Gemini 3.1 Progoogle/gemini-3.1-pro$2.00$12.00~130
Gemini 3 Flashgoogle/gemini-3-flash$0.30$1.20~1,258
Gemma 3 27Bgoogle/gemma-3-27b$0.10$0.40~3,774
Llama 4 Maverickmeta-llama/llama-4-maverick$0.20$0.85~1,786
Llama 4 Scoutmeta-llama/llama-4-scout$0.11$0.34~4,320
Llama 3.3 70Bmeta-llama/llama-3.3-70b$0.12$0.30~4,762
DeepSeek V4deepseek/deepseek-v4$0.30$1.20~1,258
DeepSeek V4 Flashdeepseek/deepseek-v4-flash$0.07$0.28~5,391
DeepSeek R2deepseek/deepseek-r2$0.55$2.19~689
Qwen3 235Bqwen/qwen3-235b$0.25$1.00~1,509
Qwen3 32Bqwen/qwen3-32b$0.10$0.30~4,878
QwQ Maxqwen/qwq-max$0.80$2.40~610
Mistral Large 3mistralai/mistral-large-3$2.00$6.00~244
Mistral Medium 3mistralai/mistral-medium-3$0.40$2.00~769
Mistral Small 3.2mistralai/mistral-small-3.2$0.10$0.30~4,878
Codestral 2mistralai/codestral-2$0.30$0.90~1,626
Grok 4x-ai/grok-4$3.00$15.00~103
Grok 4 Fastx-ai/grok-4-fast$0.20$0.50~2,857
Command Acohere/command-a$2.50$10.00~151
Command R7cohere/command-r7$0.04$0.15~10,063
Sonar Properplexity/sonar-pro$3.00$15.00~103
Sonarperplexity/sonar$1.00$1.00~1,176
Nemotron 3 Ultranvidia/nemotron-3-ultra$0.90$2.70~542
Phi-5microsoft/phi-5$0.08$0.32~4,717
Nova 2 Proamazon/nova-2-pro$0.80$3.20~472
Nova 2 Liteamazon/nova-2-lite$0.06$0.24~6,289
Jamba 2 Largeai21/jamba-2-large$2.00$8.00~189
MiniMax M3minimax/minimax-m3$0.30$1.65~939
Kimi K3moonshotai/kimi-k3$0.50$2.40~639
GLM-5z-ai/glm-5$0.55$2.19~689
Hy3tencent/hunyuan-3$0.28$1.10~1,370
MiMo V2.5xiaomi/mimo-v2.5$0.12$0.48~3,145
Ernie 5baidu/ernie-5$0.55$2.20~686
Yi 2 Large01-ai/yi-2-large$0.60$2.40~629
LFM 2 40Bliquid/lfm-2-40b$0.15$0.60~2,516
Owl Alphaopenrouter/owl-alphafreefree∞

$ per million tokens · a token ≈ ¾ of a word · an answer ≈ 250 in + 600 out