Models

openai.gpt-oss-20b-1:0

bedrock_converse · 128K ctx · 1 providers · updated 2026-09-12 05:16 UTC

Cheapest
$0.128 Official list · Bedrock Converse
Avg price
$0.140 /1M
providers
1
(3 × $0.070 + $0.300) ÷ 4 = $0.128/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.070, 3:1 $0.128, 1:1 $0.185, output only $0.300 per 1M.

The board shows this model's cheapest measured offer ($0.128/1M); the smaller figure under it is the mean of the 2 offers listed below ($0.140/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
bedrock_converse Pricebook (LiteLLM) ↗ $0.070$0.300 — — — Official list
bedrock Pricebook (LiteLLM) ↗ $0.084$0.360 — — — Official list

Price trend

Cheapest blended price, last 31 days (USD/1M): $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275 → $0.1275

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/openai.gpt-oss-20b-1.json. Free reuse requires attribution to tkx.org.

FAQ

How much does openai.gpt-oss-20b-1:0 cost?

Cheapest measured offer right now: $0.07/1M input, $0.3/1M output via bedrock_converse — across 1 tracked providers, refreshed hourly.

Who serves openai.gpt-oss-20b-1:0?

1 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of openai.gpt-oss-20b-1:0 going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings