Available Models

All models accessible through a single API endpoint. Pricing is per 1M tokens.

List Models API

GET /v1/models
Authorization: Bearer sk-bc-YOUR_API_KEY

OpenAI

Model IDInputOutputContextDescription
gpt-4o$2.50$10.00128KFlagship multimodal model — best for complex tasks
gpt-4o-mini$0.15$0.60128KFast and cost-effective for most tasks
gpt-4.1$2.00$8.001MLatest GPT model with improved coding and instruction following
gpt-4.1-mini$0.40$1.601MCompact version of GPT-4.1
gpt-4.1-nano$0.10$0.401MFastest and cheapest GPT-4.1 variant
o4-mini$1.10$4.40200KReasoning model for math, science, and coding

Anthropic

Model IDInputOutputContextDescription
claude-sonnet-4$3.00$15.00200KBest balance of intelligence and speed
claude-opus-4$15.00$75.00200KMost capable Claude model for complex analysis
claude-haiku-4$0.80$4.00200KFast and affordable for high-volume tasks
claude-3-5-sonnet$3.00$15.00200KPrevious generation Sonnet
claude-3-5-haiku$0.80$4.00200KPrevious generation Haiku

Google

Model IDInputOutputContextDescription
gemini-2.5-flash$0.15$0.601MFast multimodal model with thinking capabilities
gemini-2.5-pro$1.25$10.001MMost capable Gemini model
gemini-2.0-flash$0.10$0.401MPrevious generation Flash — ultra low cost

Model Routing

The gateway automatically routes to the correct provider based on model name prefix:

  • gpt-*, o1-*, o3-*, o4-* — OpenAI
  • claude-* — Anthropic
  • gemini-* — Google

Automatic Failover

If a provider returns a 5xx error or times out, the gateway automatically retries with a fallback provider. This happens transparently — you see a successful response from the fallback.