Claude Code
Cursor
Codex
OpenCodeEvery model. One key.Up to 70% off.
Claude, GPT and Gemini — 35+ models behind one OpenAI-compatible key and one base URL. Same weights, same quality, a fraction of the official API bill. Compare every price below.
Official price vs Luno
USD per 1 million tokens. Luno rates are the effective prices inside any flat plan — every model, every plan.
| Model | Context | Official $/1M | Luno $/1M | Savings |
|---|---|---|---|---|
Claude Fable 5POPULAR claude-fable-5 | 1M | $10.00 / $50.00 | $3.00 / $15.00 | -70% |
Claude Opus 4.8POPULAR claude-opus-4.8 | 1M | $5.00 / $25.00 | $1.50 / $7.50 | -70% |
Claude Opus 4.7 claude-opus-4.7 | 1M | $5.00 / $25.00 | $1.50 / $7.50 | -70% |
Claude Opus 4.6 claude-opus-4.6 | 1M | $5.00 / $25.00 | $1.50 / $7.50 | -70% |
Claude Opus 4.5 claude-opus-4.5 | 200K | $5.00 / $25.00 | $1.50 / $7.50 | -70% |
Claude Sonnet 4.6POPULAR claude-sonnet-4.6 | 1M | $3.00 / $15.00 | $0.90 / $4.50 | -70% |
Claude Sonnet 4.5 claude-sonnet-4.5 | 1M | $3.00 / $15.00 | $0.90 / $4.50 | -70% |
Claude Sonnet 4 claude-sonnet-4 | 200K | $3.00 / $15.00 | $0.90 / $4.50 | -70% |
Claude Haiku 4.5POPULAR claude-haiku-4.5 | 200K | $1.00 / $5.00 | $0.30 / $1.50 | -70% |
Claude Haiku 4 claude-haiku-4 | 200K | $0.80 / $4.00 | $0.24 / $1.20 | -70% |
Claude 3.7 Sonnet claude-3.7-sonnet | 200K | $3.00 / $15.00 | $0.90 / $4.50 | -70% |
Claude 3.5 Sonnet claude-3.5-sonnet | 200K | $3.00 / $15.00 | $0.90 / $4.50 | -70% |
Claude 3.5 Haiku claude-3.5-haiku | 200K | $0.80 / $4.00 | $0.24 / $1.20 | -70% |
GPT-5.5POPULAR gpt-5.5 | 400K | $5.00 / $30.00 | $1.50 / $9.00 | -70% |
GPT-5.4 gpt-5.4 | 400K | $3.00 / $18.00 | $0.90 / $5.40 | -70% |
GPT-5.4 MiniPOPULAR gpt-5.4-mini | 400K | $0.60 / $3.60 | $0.18 / $1.08 | -70% |
GPT-5.3 gpt-5.3 | 400K | $2.50 / $15.00 | $0.75 / $4.50 | -70% |
GPT-5.1 gpt-5.1 | 400K | $2.00 / $12.00 | $0.60 / $3.60 | -70% |
GPT-5 gpt-5 | 400K | $1.75 / $10.00 | $0.53 / $3.00 | -70% |
GPT-5 Mini gpt-5-mini | 400K | $0.45 / $2.40 | $0.14 / $0.72 | -70% |
GPT-5 Nano gpt-5-nano | 400K | $0.10 / $0.40 | $0.03 / $0.12 | -70% |
o4 o4 | 200K | $4.00 / $16.00 | $1.20 / $4.80 | -70% |
o4-mini o4-mini | 200K | $1.10 / $4.40 | $0.33 / $1.32 | -70% |
o3 o3 | 200K | $2.00 / $8.00 | $0.60 / $2.40 | -70% |
GPT-4.1 gpt-4.1 | 1M | $2.00 / $8.00 | $0.60 / $2.40 | -70% |
GPT-4.1 Mini gpt-4.1-mini | 1M | $0.40 / $1.60 | $0.12 / $0.48 | -70% |
GPT-4o gpt-4o | 128K | $2.50 / $10.00 | $0.75 / $3.00 | -70% |
GPT-4o Mini gpt-4o-mini | 128K | $0.15 / $0.60 | $0.05 / $0.18 | -70% |
Gemini 3.1 ProPOPULAR gemini-3.1-pro | 1M | $2.50 / $15.00 | $0.75 / $4.50 | -70% |
Gemini 3.5 FlashPOPULAR gemini-3.5-flash | 1M | $0.15 / $0.60 | $0.05 / $0.18 | -70% |
Gemini 3 Pro gemini-3-pro | 1M | $2.00 / $12.00 | $0.60 / $3.60 | -70% |
Gemini 3 Flash gemini-3-flash | 1M | $0.12 / $0.50 | $0.04 / $0.15 | -70% |
Gemini 2.5 Pro gemini-2.5-pro | 1M | $1.25 / $10.00 | $0.38 / $3.00 | -70% |
Gemini 2.5 Flash gemini-2.5-flash | 1M | $0.30 / $2.50 | $0.09 / $0.75 | -70% |
Gemini 2.5 Flash-Lite gemini-2.5-flash-lite | 1M | $0.10 / $0.40 | $0.03 / $0.12 | -70% |
Gemini 2.0 Flash gemini-2.0-flash | 1M | $0.10 / $0.40 | $0.03 / $0.12 | -70% |
Gemini 1.5 Pro gemini-1.5-pro | 2M | $1.25 / $5.00 | $0.38 / $1.50 | -70% |
Gemini 1.5 Flash gemini-1.5-flash | 1M | $0.08 / $0.30 | $0.02 / $0.09 | -70% |
Prices shown as input / output per 1M tokens. Official rates are provider list prices; Luno rates are effective in-plan prices.
Why is it 70% cheaper?
Flat monthly plans
You pay one predictable subscription, not per-token invoices that explode mid-month. Plans start at $6.99/mo and every plan includes every model in this table.
Bulk-reserved compute
Luno reserves provider capacity in bulk and at enterprise rates, then passes the discount on. That is how the same Claude Opus 4.8 costs 70% less here — same model, cheaper seat.
No markup on top of plans
The prices in this table are effective rates inside your plan. There are no hidden per-request fees, no "premium model" surcharges and no surprise overage multipliers.
Model questions, answered
Yes. Every plan — from Starter to Enterprise — unlocks the full catalog: Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro and everything below them. Plans differ only in monthly usage volume, never in which models you can call.
Usually within 24–48 hours of the official release. The moment a provider ships a new model to their API, we add it to the gateway and it becomes available under the same key — no migration, no new endpoint.
Yes. Luno routes your requests to the same models with the same weights — we are a gateway, not a re-trained clone or a quantized mirror. Same outputs, same context windows, same capabilities, just a lower bill.
Change one string. Your key works for every model, so switching from GPT-5.5 to Claude Opus 4.8 is just editing the `model` field in your request body. Base URL stays https://api.luno.codes/v1 for everything.