Models

gpt-oss-120b

openai ↗ · 131K ctx · 30 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.065 via OpenRouter
Avg price
$0.253 /1M
providers
30
Tokens (24h)
81B
Volume (24h)
$5.7K est.
(3 × $0.030 + $0.170) ÷ 4 = $0.065/1M — 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 $0.030, 3:1 $0.065, 1:1 $0.100, output only $0.170 per 1M.

The board shows this model's cheapest measured offer ($0.065/1M); the smaller figure under it is the mean of the 48 offers listed below ($0.253/1M). Add those up and divide — it matches. 24h token volume (81B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
CoreWeave (fp4) OpenRouter $0.030$0.170 407ms 36 99.7% API-measured
deepinfra HuggingFace Router $0.037$0.170 1784ms 40 API-measured
DeepInfra (bf16) OpenRouter $0.037$0.170 519ms 38 99.8% API-measured
novita Pricebook (LiteLLM) $0.050$0.250 Official list
novita HuggingFace Router $0.050$0.250 458ms 66 API-measured
novita-ai Novita AI $0.050$0.250 API-measured
Novita (fp4) OpenRouter $0.050$0.250 500ms 88 100% API-measured
deepinfra Pricebook (LiteLLM) $0.050$0.450 Official list
SiliconFlow (fp8) OpenRouter $0.050$0.450 1243ms 19 100% API-measured
Google (global) OpenRouter $0.090$0.360 310ms 173 99.9% API-measured
ovhcloud Pricebook (LiteLLM) $0.080$0.400 Official list
DigitalOcean OpenRouter $0.070$0.490 502ms 38 100% API-measured
nscale HuggingFace Router $0.100$0.400 462ms 107 API-measured
ovhcloud HuggingFace Router $0.090$0.470 502ms 147 API-measured
baseten Pricebook (LiteLLM) $0.100$0.500 Official list
baseten HuggingFace Router $0.100$0.500 262ms 95 API-measured
BaseTen (fp4) OpenRouter $0.100$0.500 320ms 151 100% API-measured
Mancer 2 (fp8) OpenRouter $0.100$0.500 925ms 58 99.6% API-measured
azure_ai Pricebook (LiteLLM) $0.150$0.600 Official list
fireworks_ai Pricebook (LiteLLM) $0.150$0.600 Official list
groq Pricebook (LiteLLM) $0.150$0.600 Official list
together_ai Pricebook (LiteLLM) $0.150$0.600 Official list
watsonx Pricebook (LiteLLM) $0.150$0.600 Official list
scaleway Pricebook (LiteLLM) $0.150$0.600 Official list
tensormesh Pricebook (LiteLLM) $0.150$0.600 Official list
together HuggingFace Router $0.150$0.600 251ms 111 API-measured
fireworks-ai HuggingFace Router $0.150$0.600 1652ms 72 API-measured
requesty Requesty $0.150$0.600 API-measured
Amazon Bedrock OpenRouter $0.150$0.600 495ms 147 99.9% API-measured
DeepInfra (turbo) OpenRouter $0.150$0.600 507ms 127 100% API-measured
Together OpenRouter $0.150$0.600 320ms 64 100% API-measured
Nebius (fp4) OpenRouter $0.150$0.600 325ms 149 98.6% API-measured
Amazon Bedrock (eu-west-1) OpenRouter $0.150$0.600 API-measured
Phala OpenRouter $0.150$0.600 582ms 92 100% API-measured
Groq OpenRouter $0.150$0.600 227ms 318 100.0% API-measured
Parasail (fp4) OpenRouter $0.100$0.750 370ms 98 89.5% API-measured
groq HuggingFace Router $0.150$0.750 270ms 423 API-measured
Mara OpenRouter $0.150$0.750 96.3% API-measured
sambanova Pricebook (LiteLLM) $0.220$0.590 Official list
replicate Pricebook (LiteLLM) $0.180$0.720 Official list

Who burns this model

Top apps routing traffic to this model over the last 30 days, via OpenRouter's public stats. Only apps that opted into tracking appear, and only the top few are published — this is not the full demand picture. These figures are a 30-day window and are NOT comparable with the cumulative totals on the Apps board.

AppTokens (30d)Requests
Mira is the leading AI agent inside Telegram 110B 15M
cvi-magic-tasks-ai-tagging 25B 6M
Craft 22B 6M
OpenClaw 20B 760K
Hermes Agent 11B 395K

Volume trend

94B 30d d-29 · 66B tokensd-28 · 75B tokensd-27 · 84B tokensd-26 · 81B tokensd-25 · 69B tokensd-24 · 67B tokensd-23 · 78B tokensd-22 · 72B tokensd-21 · 82B tokensd-20 · 94B tokensd-19 · 90B tokensd-18 · 72B tokensd-17 · 62B tokensd-16 · 57B tokensd-15 · 68B tokensd-14 · 67B tokensd-13 · 72B tokensd-12 · 75B tokensd-11 · 63B tokensd-10 · 60B tokensd-9 · 66B tokensd-8 · 74B tokensd-7 · 87B tokensd-6 · 76B tokensd-5 · 81B tokensd-4 · 78B tokensd-3 · 77B tokensd-2 · 70B tokensd-1 · 66B tokensd-0 · 81B tokens

Last 30 days: 66B → 81B (+24%); range 57B–94B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

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/gpt-oss-120b.json. Free reuse requires attribution to tkx.org.

About

GPT-OSS-120b is a large language model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language processing tasks.

AI-generated summary from public information — is this yours?

FAQ

How much does gpt-oss-120b cost?

Cheapest measured offer right now: $0.03/1M input, $0.17/1M output via CoreWeave (fp4) — across 30 tracked providers, refreshed hourly.

Who serves gpt-oss-120b?

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

How heavily is gpt-oss-120b used?

gpt-oss-120b routed 81B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings