Frontier intelligence, unified.
Access the world's leading reasoning, vision, and coding models through one consistent API. Context windows and token prices are updated live and verified directly with provider labs.
Claude 3.5 Sonnet
claude-3-5-sonnetAnthropic's premier model for nuanced reasoning, software engineering, and high-precision document synthesis.
GPT-4o
gpt-4oOpenAI flagship omni model with high-speed intelligence across text, vision, and structured schema generation.
GPT-4o mini
gpt-4o-miniAffordable and exceptionally fast lightweight model for everyday tasks, triage, and high-frequency queries.
Gemini 1.5 Pro
gemini-1-5-proGoogle frontier model featuring industry-leading 2M token context window for massive repos, long docs, and media.
Gemini 1.5 Flash
gemini-1-5-flashHigh-throughput, cost-effective multimodal model with a 1M token context window built for rapid response times.
Llama 3.3 70B Instruct
llama-3-3-70b-instructMeta's most capable open-weights instruction model, rivaling closed models on code generation, reasoning, and math.
DeepSeek R1
deepseek-r1Open-weights reasoning model utilizing large-scale reinforcement learning for complex step-by-step proofs and code.
Token Spend Estimator
Estimate your monthly compute budget across frontier models based on expected traffic volume.
| Model | Provider | Estimated Spend | Credits Required | Action |
|---|---|---|---|---|
| Claude 3.5 Sonnet | anthropic | $10.50 | 1,050 cr | Test in Studio |
| GPT-4o | openai | $7.50 | 750 cr | Test in Studio |
| GPT-4o mini | openai | $0.45 | 45 cr | Test in Studio |
| Gemini 1.5 Pro | $8.75 | 875 cr | Test in Studio | |
| Gemini 1.5 Flash | $0.22 | 22 cr | Test in Studio |