LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT OSS 120B

openai·openai/gpt-oss-120b·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·LLM GatewayGateway
$0.029 / $0.15
Blended $0.058 · 100.3× spread
2 more $0 channels
Context
131,000
Output limit
131,000
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
TextImage
Weights
Hugging Face

GPT OSS 120B by openai is offered by 109 providers on this page. Public prices are shown for 106 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is LLM Gateway at $0.029 / $0.145 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 100× across the providers that host it. It also has 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 3.8 on the Intelligence Index, with 11.2 for Engineering, its strongest domain. Against its lowest blended price of $0.058 per 1M, that is roughly 65 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 252 tokens per second, with 0.76s to the first token. Running one task of the Artificial Analysis suite costs about $0.3453, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 131,000 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. Accepted input modalities are Text and Image. 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 High

Intelligence3.8
Value65
Engineering11.2
Finance & Accounting7.8
Legal8.1
Healthcare & Medical5.8
Strategy & Ops5.5
Economics9
Output speed252 tok/s
TTFT0.76 s
Cost per task$0.35
Value formulaIQ 3.8 ÷ min blended $0.058 = 65

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

Available at 109 providers106 with public prices · 2 free

  • ProviderInput / Output
  • PendraGateway
    gpt-oss:120b
    Free
    Context 131,072 ⚠Output limit 131,072
  • QVACGateway
    Free
    Context 131,072 ⚠Output limit 131,072deprecated
  • LLM GatewayGateway
    $0.029 / $0.15
    Cache read $0.0044Context 131,072 ⚠Output limit 131,072
  • DevPass (LLM Gateway)Gateway
    $0.029 / $0.15
    Cache read $0.0044Context 131,072 ⚠Output limit 32,766
  • NanoGPTGateway
    $0.03 / $0.15
    Cache read $0.03Context 128,000 ⚠Output limit 16,384
  • Eden AIGateway
    $0.03 / $0.15
    Cache read $0.0045Context 131,072 ⚠Output limit 131,072
  • Kilo GatewayGateway
    $0.03 / $0.15
    Cache read $0.015Context 131,072 ⚠Output limit 117,964
  • CoreWeaveCloud
    $0.03 / $0.17
    Cache read $0.03Context 131,072 ⚠Output limit 131,072
  • OrcaRouterGateway
    $0.03 / $0.17
    Context 131,072 ⚠Output limit 131,072deprecated
  • HeliconeGateway
    $0.04 / $0.16
    Context 131,072 ⚠Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Pendra
gpt-oss:120b
GatewayFree——131,072 ⚠131,072
QVACGatewayFree——131,072 ⚠131,072deprecated
LLM GatewayGateway$0.029$0.15$0.0044—131,072 ⚠131,072
DevPass (LLM Gateway)Gateway$0.029$0.15$0.0044—131,072 ⚠32,766
NanoGPTGateway$0.03$0.15$0.03—128,000 ⚠16,384
Eden AIGateway$0.03$0.15$0.0045—131,072 ⚠131,072
Kilo GatewayGateway$0.03$0.15$0.015—131,072 ⚠117,964
CoreWeaveCloud$0.03$0.17$0.03—131,072 ⚠131,072
OrcaRouterGateway$0.03$0.17——131,072 ⚠131,072deprecated
HeliconeGateway$0.04$0.16——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 = nonebudget_tokens ≥ 128 ≤ 32,768effort = minimaleffort = xhigheffort = maxToggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 16 of 109 providers.

8 / 109 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1LLM Gateway$10.13
2DevPass (LLM Gateway)$10.13
3Eden AI$10.44
4Kilo Gateway$11.70
5Runcrate$12.73
6Kenari$13.31

2 more channels offer $0 (Pendra, QVAC); 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
$0.06$02026-08-052026-11-18
2026-11-18Input list —Output list —Min blended $0.058

Artificial Analysis evaluations29 items

GPQA Diamond78.2%
Humanity's Last Exam19.6%
HLE-Diamond3.8%
CritPt1.1%
CritPt v2 Hard4.0%
SciCode34.0%
LiveCodeBench87.8%
FrontierCode1.2%
FrontierCode 2.00.0%
Terminal-Bench Hard23.5%
Terminal-Bench 2.126.2%
Terminal-Bench 4.00.0%
Terminal-Bench-Science0.0%
AIME 202593.4%
τ²-Bench Telecom65.8%
τ³-Bench Banking12.8%
AutomationBench-AA0.2%
APEX-Agents-AA3.1%
EnterpriseOps-Gym-AA25.5%
ITBench-AA5.7%
AA-Briefcase0
GDPval-AA616
GDP.pdf4.2%
AA-LCR52.0%
MLCR-AA1.7%
IFBench69.0%
AA-Omniscience Index-46.4
AA-Omniscience Accuracy21.7%
AA-Omniscience Non-Hallucination13.1%

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 20Bsame series—GPT Luna Latestsame lab—
Data partly from models.dev (MIT)