Modèles frontière, 30 % sous le tarif officiel.
Chaque modèle 30 % sous le tarif officiel du fournisseur, accessible via la même interface compatible OpenAI. Cliquez sur un modèle pour voir paramètres, capacités et exemples de code.
Claude Opus 4.7
Anthropic's newest Opus — flagship reasoning, vision, 200K context.
Claude Opus 4.6
Anthropic Opus 4.6 — deep reasoning, exceptional agentic ability.
Claude Sonnet 4.6
Balanced speed/quality — the everyday production workhorse, elite coding.
Claude Sonnet 4.5
Anthropic Sonnet 4.5 — production workhorse.
Claude Haiku 4.5
Anthropic Haiku 4.5 — fast and cost-efficient.
Gemini 3 Pro
Google's flagship — native multimodal, 1M+ context, chain-of-thought.
Gemini 3.1 Pro
Latest Gemini 3.1 Pro — incremental quality bump.
Gemini 3 Flash
Cost-efficient Gemini — millisecond responses for high-frequency calls.
Gemini 2.5 Pro
Previous-gen Gemini Pro — strong reasoning and vision.
Gemini 2.5 Flash
Previous-gen Gemini Flash — extreme value.
Nano Banana
Gemini's native image generation — strong character consistency.
Nano Banana 2
Newer Nano Banana — improved fidelity and prompt adherence.
Nano Banana Pro
Google's premium Nano Banana — top-tier fidelity and instruction following.
GPT-Image-2
OpenAI's latest native image model — strong prompt understanding.
Nano Banana Edit
Image-to-image editor — multi-turn edits with consistency.
GPT-Image-2 Edit
GPT-Image-2 image-to-image — edit and remix existing images.
Veo 3 Fast
Google Veo 3 Fast — native audio, cinematic quality at the cheapest tier.
Veo 3 Quality
Google Veo 3 Quality tier — best fidelity, slower + pricier than Fast.
Veo 3 Lite
Google Veo 3 Lite — the budget tier for storyboarding and previews.