LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT OSS 20B

openai·openai/gpt-oss-20b·GA·Open weights·gpt-oss series
Open GPT reasoning model for self-hosted agents and controllable deployments

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Eden AIGateway
$0.009 / $0.045
Blended $0.018 · 22.2× spread
4 more $0 channels
Context
32,768
Output limit
32,768
Knowledge cutoff
2024-06
Released / updated
2025-08-05 / 2025-08-05
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

GPT OSS 20B by openai is offered by 57 providers on this page. Public prices are shown for 52 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Eden AI at $0.009 / $0.045 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 22× across the providers that host it. It also has 4 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 113 tokens per second, with 0.95s to the first token.

The context window is 32,768 tokens at the reference host, but hosts report different limits, from 32,768 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-06.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Low

Intelligence—
Value—
Output speed113 tok/s
TTFT0.95 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 57 providers52 with public prices · 4 free

  • ProviderInput / Output
  • QVACGateway
    Free
    Context 131,072 ⚠Output limit 131,072
  • NvidiaCloud
    Free
    Context 131,072 ⚠Output limit 131,072
  • InferAllGateway
    Free
    Context 131,072 ⚠Output limit 131,072
  • LMStudioCloud
    Free
    Context 131,072 ⚠Output limit 131,072
  • Eden AIGateway
    $0.009 / $0.045
    Cache read $0.0045Context 131,072 ⚠Output limit 131,072
  • SOKKAN RouterGateway
    $0.015 / $0.075
    Cache read $0.008Context 65,536 ⚠Output limit 65,536
  • NanoGPTGateway
    $0.018 / $0.09
    Cache read $0.009Context 131,072 ⚠Output limit 16,384
  • OpenRouterGateway
    $0.018 / $0.09
    Cache read $0.009Context 131,072 ⚠Output limit 117,964
  • Eden AIGateway
    $0.018 / $0.09
    Cache read $0.0027Context 131,072 ⚠Output limit 131,072
  • Eden AIGateway
    flexai/gpt-oss-20b@eu
    $0.018 / $0.09
    Cache read $0.0027Context 131,072 ⚠Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
QVACGatewayFree——131,072 ⚠131,072
NvidiaCloudFree——131,072 ⚠131,072
InferAllGatewayFree——131,072 ⚠131,072
LMStudioCloudFree——131,072 ⚠131,072
Eden AIGateway$0.009$0.045$0.0045—131,072 ⚠131,072
SOKKAN RouterGateway$0.015$0.075$0.008—65,536 ⚠65,536
NanoGPTGateway$0.018$0.09$0.009—131,072 ⚠16,384
OpenRouterGateway$0.018$0.09$0.009—131,072 ⚠117,964
Eden AIGateway$0.018$0.09$0.0027—131,072 ⚠131,072
Eden AI
flexai/gpt-oss-20b@eu
Gateway$0.018$0.09$0.0027—131,072 ⚠131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = higheffort = noneToggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 5 of 57 providers.

6 / 57 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Eden AI$3.51
2SOKKAN Router$5.91
3Eden AI$6.26
4Eden AI$6.26
5NanoGPT$7.02
6OpenRouter$7.02

4 more channels offer $0 (QVAC, Nvidia, InferAll etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.055$02026-08-052026-11-09
2026-11-09Input list —Output list —Min blended $0.018

Artificial Analysis evaluations9 items

GPQA Diamond61.1%
Humanity's Last Exam5.3%
CritPt0.0%
LiveCodeBench65.2%
Terminal-Bench Hard4.5%
AIME 202562.3%
τ²-Bench Telecom50.3%
AA-LCR31.0%
IFBench57.8%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

GPT OSS Safeguard 20Bsame series—GPT OSS Safeguard 120Bsame series—GPT OSS 120Bsame series—
Data partly from models.dev (MIT)