Models
Browse all available models. Prices shown per 1M tokens (unless otherwise noted).
| Model | Provider | Context | Input | Output | Features |
|---|---|---|---|---|---|
GPT-4o gpt-4o | OpenAI | 128K | €2.50 | €10.00 | VisionFunction CallingJSON Mode |
GPT-4o Mini gpt-4o-mini | OpenAI | 128K | €0.15 | €0.60 | VisionFunction CallingJSON Mode |
O1 o1 | OpenAI | 200K | €15.00 | €60.00 | ReasoningFunction Calling |
O3 Mini o3-mini | OpenAI | 200K | €1.10 | €4.40 | ReasoningFast |
GPT-4 Turbo gpt-4-turbo | OpenAI | 128K | €10.00 | €30.00 | VisionFunction CallingJSON Mode |
Claude 3.5 Sonnet claude-3.5-sonnet | Anthropic | 200K | €3.00 | €15.00 | VisionExtended Context |
Claude 3.5 Haiku claude-3.5-haiku | Anthropic | 200K | €0.80 | €4.00 | VisionFast |
Claude 3 Opus claude-3-opus | Anthropic | 200K | €15.00 | €75.00 | VisionMost Capable |
Gemini 2.0 Flash gemini-2.0-flash | 1M | €0.075 | €0.30 | VisionAudioVideoGrounding | |
Gemini 1.5 Pro gemini-1.5-pro | 2M | €1.25 | €5.00 | VisionAudioVideoLongest Context | |
Llama 3.3 70B llama-3.3-70b | Meta | 128K | €0.60 | €0.90 | Open SourceFast |
Llama 3.2 90B Vision llama-3.2-90b-vision | Meta | 128K | €0.90 | €0.90 | VisionOpen Source |
Mistral Large mistral-large | Mistral | 128K | €2.00 | €6.00 | Function CallingJSON Mode |
Mixtral 8x7B mixtral-8x7b | Mistral | 32K | €0.24 | €0.24 | MoEOpen Source |
Text Embedding 3 Small text-embedding-3-small | OpenAI | 8K | €0.02 | - | 1536 dimsRecommended |
Text Embedding 3 Large text-embedding-3-large | OpenAI | 8K | €0.13 | - | 3072 dimsBest Quality |
DALL-E 3 dall-e-3 | OpenAI | - | €0.04 | - | HDWide |
FLUX 1.1 Pro flux-1.1-pro | Black Forest Labs | - | €0.04 | - | FastHigh Quality |
Stable Diffusion 3 stable-diffusion-3 | Stability AI | - | €0.03 | - | Open SourceCustomizable |
Whisper whisper-1 | OpenAI | - | €0.006/min | - | TranscriptionTranslation |
TTS-1 tts-1 | OpenAI | - | €15.00/1M chars | - | Text-to-Speech6 Voices |
TTS-1 HD tts-1-hd | OpenAI | - | €30.00/1M chars | - | HD Audio6 Voices |
Model Categories
Choosing a Model
Best Overall: GPT-4o
Excellent balance of quality, speed, and cost. Supports vision, function calling, and JSON mode. Great for most applications.
Best Value: GPT-4o Mini
90% of GPT-4o's capability at 6% of the cost. Perfect for high-volume applications or cost-sensitive use cases.
Best for Long Context: Gemini 1.5 Pro
2 million token context window—process entire books, codebases, or hours of video transcripts in a single request.
Best for Complex Reasoning: O1 / Claude Opus
When accuracy matters most—research, analysis, complex coding problems, or multi-step reasoning tasks.
Best Open Source: Llama 3.3 70B
Competitive with proprietary models at a fraction of the cost. Great for fine-tuning or self-hosting options.
💡 About Pricing
Prices shown are per 1 million tokens for chat/embedding models. Actual costs may vary based on your usage tier. Image and audio models have per-unit pricing. Check your billing dashboard for current rates.