AI Calculator Pro

GPT OSS 20B

OpenAI · model · context window 131,072 tokens.

Pricing (per 1M tokens)

Input$0.00900
Output$0.0450
Cache read$0.00450

Specifications

Context window131,072 tokens
Max output32,768 tokens
Modalitiestext
VisionNo
Tool useYes
ReasoningNo
Prompt cachingNo

GPT OSS 20B has had 10 tracked price changes since we began monitoring. Most recent: cached input $0.00500 → $0.00900 on 5 October 2026. All-time low input rate: $0.00900/1M.

Input price over time ($/1M tokens)
Low $0.009High $0.030

Recorded from our daily pricing checks. See the full LLM price tracker.

Where else you can run GPT OSS 20B

The same model is resold by 28 providers we track. The typical one charges 4.8× what the cheapest does — $0.0850 against $0.0180 per 1M tokens, blended 3:1. Routing the same workload to a different host is often a bigger saving than switching model.

ProviderInput / 1MOutput / 1MBlended
Edenai$0.00900$0.0450$0.0180
Kilo$0.0180$0.0900$0.0360
OpenRouter ↗$0.0180$0.0900$0.0360
Wandb$0.0300$0.1300$0.0550
DeepInfra ↗$0.0300$0.1400$0.0580
IO NET$0.0300$0.1400$0.0580
Vercel AI Gateway$0.0300$0.1400$0.0580
Merge Gateway$0.0400$0.1500$0.0680
Siliconflow$0.0400$0.1800$0.0750
Cortecs$0.0450$0.1670$0.0760

Showing the 10 cheapest of 28. The full list for every model is in the open endpoint dataset.

Third-party listings via models.dev, not rates we verify with each host the way we do first-party pricing. Treat them as a shortlist to check, not a quote — and confirm quantisation, context limits and rate limits before switching, since a cheaper host is not always serving the same thing.

Estimate cost with GPT OSS 20B

GPT OSS 20B is pre-selected below. Enter your token counts and volume to see the cost per request, per day and per month — then switch models to compare.

Results update automatically as you type.

Result
$0.0000315 per request
~$0.9450/month at 1,000 requests/day
Input cost
$0.00000900
Output cost
$0.0000225
Per request
$0.0000315
Per day
$0.0315
Per month
$0.9450

Source: community-hosted (cheapest of 28 providers, edenai via models.dev). Prices are re-checked daily against the provider’s official pricing; this rate was last changed on 11 October 2026. A recent date here just means the price is still current, not that it moved.