Featured · Anthropic
The Claude line — pick your tier.
Opus for the hardest reasoning, Sonnet for everyday production, Haiku for high-volume speed — every one on the same balance, billed below list.
Claude Opus 4.8
AnthropicAnthropic's most capable model — deep reasoning, long agentic runs, and the hardest coding and analysis.
- Input / 1M
- $5.00$3.50
- Output / 1M
- $25.00$17.50
Claude Sonnet 4.6
AnthropicThe everyday Claude: frontier quality at a balanced rate — the default for production work.
- Input / 1M
- $3.00$2.10
- Output / 1M
- $15.00$10.50
Claude Haiku 4.5
AnthropicFast, low-cost Claude for high-volume, latency-sensitive tasks.
- Input / 1M
- $1.00$0.75
- Output / 1M
- $5.00$3.75
Browse
Every model, one balance.
Top up once and switch between GPT, Claude and Gemini — no new accounts, no separate contracts.
See pricingOpenAI: GPT-5.5
OpenAI's flagship for logic-heavy, multi-step tasks and tool use.
Anthropic: Claude Opus 4.8
Anthropic's most capable model — deep reasoning, long agentic runs, and the hardest coding and analysis.
Anthropic: Claude Sonnet 4.6
The everyday Claude: frontier quality at a balanced rate — the default for production work.
Google: Gemini 2.5 Pro
Google's frontier model with a 1M-token context for long documents and codebases.
OpenAI: GPT-5.4
Strong all-rounder — coding, instruction-following and agents at a lower rate.
OpenAI: GPT-5.4 mini
Compact GPT-5.4 for cheap, fast, high-throughput calls.
Google: Gemini 2.5 Flash
Fast Gemini tuned for speed and price at scale.
Anthropic: Claude Haiku 4.5
Fast, low-cost Claude for high-volume, latency-sensitive tasks.
Google: Gemini 2.5 Flash-Lite
The cheapest Gemini — lightweight, high-volume extraction and classification.
Token models are priced per 1M tokens (input / output), with a cached-input rate where supported. Verify any figure against the provider's own pricing page.
Pick a model and make your first call tonight.
One OpenAI-compatible base URL, one prepaid balance, no per-vendor accounts.