Skip to content
All Guides

Supported Models

Bear Lumen tracks costs for 31 models across 9 providers. The SDK auto-detects the provider and model from API responses.

Rates shown are per million tokens (USD). Prices sourced from provider pricing pages and may change. Bear Lumen rate cards are updated regularly.

OpenAI

9 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
GPT-4ogpt-4o$2.50$10.00
GPT-4o Minigpt-4o-mini$0.15$0.60
GPT-4.1gpt-4.1$2.00$8.00
GPT-4 Turbogpt-4-turbo$10.00$30.00
GPT-3.5 Turbogpt-3.5-turbo$0.50$1.50
O1o1$15.00$60.00
O3o3$2.00$8.00
O3 Minio3-mini$1.10$4.40
O4 Minio4-mini$1.10$4.40

Anthropic

8 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Claude Sonnet 4claude-sonnet-4$3.00$15.00
Claude Sonnet 4.5claude-sonnet-4-5$3.00$15.00
Claude Opus 4claude-opus-4$15.00$75.00
Claude Opus 4.5claude-opus-4-5$5.00$25.00
Claude Haiku 3claude-haiku-3$0.25$1.25
Claude Haiku 4.5claude-haiku-4-5$1.00$5.00
Claude 3.5 Sonnetclaude-3-5-sonnet$3.00$15.00
Claude 3 Opusclaude-3-opus$15.00$75.00

Google

7 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Gemini 2.0 Flashgemini-2.0-flash$0.10$0.40
Gemini 2.5 Flashgemini-2.5-flash$0.30$2.50
Gemini 2.5 Flash Litegemini-2.5-flash-lite$0.10$0.40
Gemini 2.5 Progemini-2.5-pro$1.25$10.00
Gemini 1.5 Progemini-1.5-pro$1.25$5.00
Gemini 1.5 Flashgemini-1.5-flash$0.075$0.30
Gemini 3 Pro Previewgemini-3-pro-preview$2.00$12.00

Mistral

2 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Mistral Largemistral-large$2.00$6.00
Mistral Smallmistral-small$0.20$0.60

Together AI

1 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct$0.88$0.88

Groq

1 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Llama 3.3 70B Versatilellama-3.3-70b-versatile$0.59$0.79

ElevenLabs

1 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
ElevenLabs Multilingual V2eleven_multilingual_v2$300.00$0.000

Deepgram

1 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Deepgram Nova 2nova-2$4.30$0.000

Stability AI

1 models supported

ModelBase NameInput (per 1M tokens)Output (per 1M tokens)
Stable Diffusion 3 Mediumsd3-medium$35000.00$0.000

Don't see your model?

Bear Lumensupports any model with token-based pricing. If your provider isn't listed, request support and we'll add it to the rate card catalog.

Request model support

How model detection works

The Bear Lumen SDK inspects the API response to identify the provider and model automatically. Pass the raw provider response to bear.track(response) and costs are calculated using the matching rate card. For models not in the catalog, costs are tracked as zero until a rate card is added.