Pricing / Ultra-low-latency token streaming
Cheapest price per million input tokens for Ultra-low-latency token streaming
Unit: usd_per_million_input_tokens only — nothing converted or blended. min sourced input SKU among candidates; not quality-adjusted. Updated 2026-10-27 (newest asOf / re-check on this page).
Pick is the cheapest sourced input $/1M among candidates (0.075).
| # | Provider | SKU | Input $/1M | Source | asOf / re-checked | First seen / last changed |
|---|---|---|---|---|---|---|
| 1 | GroqDepot Pick | openai/gpt-oss-20b | $0.075 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 2 | FriendliAI | gemma-4-31B-it | $0.14 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 3 | SambaNova | gpt-oss-120b | $0.22 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 4 | Cerebras | gpt-oss-120b | $0.35 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
Price only: not quality-, latency- or limit-adjusted. The Depot Pick is editorial and is not chosen by price. Brief: /jtbds/ultra-low-latency · Agents: GET /api/quote?jtbd=ultra-low-latency