theserverless.dev InferenceList

Compare

Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.

Llama 3.1 Nemotron 70B Instruct HF ×OpenAI: GPT-5.2 (batch) ×

Monthly bill

Token models use the token counts. Other models use units times the flat rate.

Llama 3.1 Nemotron 70B Instruct HF$1.76
OpenAI: GPT-5.2 (batch)$7.88

Lowest bill: Llama 3.1 Nemotron 70B Instruct HF · $1.76

Add another

Search by name, then add up to four.

Llama 3.1 Nemotron 70B Instruct HFOpenAI: GPT-5.2 (batch)
ProviderTogetherOpenAI
Modalitytexttext, image
Context33K400K
Input$0.88/1M$0.875/1M
Output$0.88/1M$7/1M
Cache readNot published—$0.0875/1M
Tiers and extras
Llama 3.1 Nemotron 70B Instruct HF
—
OpenAI: GPT-5.2 (batch)
Web search: $0.01 per request