The board shows this model's cheapest measured offer ($0.052/1M); the smaller figure under it is the mean of the 60 offers listed below ($0.222/1M). Add those up and divide — it matches. 24h token volume (55B) 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.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| PrimeIntellect (fp4) | OpenRouter ↗ | $0.031 | $0.115 | 594ms | 81 | 100% | API-measured |
| requesty | Requesty ↗ | $0.032 | $0.140 | — | — | — | API-measured |
| Near AI (fp4) | OpenRouter ↗ | $0.030 | $0.150 | 662ms | 71 | 100% | API-measured |
| Venice (int4) | OpenRouter ↗ | $0.030 | $0.150 | 784ms | 48 | 100% | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $0.030 | $0.170 | — | — | — | Official list |
| CoreWeave (fp4) | OpenRouter ↗ | $0.030 | $0.170 | 318ms | 76 | 100% | API-measured |
| DekaLLM (bf16) | OpenRouter ↗ | $0.030 | $0.180 | 523ms | 75 | 100% | API-measured |
| AkashML (bf16) | OpenRouter ↗ | $0.030 | $0.187 | 318ms | 108 | 100% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.037 | $0.170 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $0.037 | $0.170 | 263ms | 50 | — | API-measured |
| DeepInfra (bf16) | OpenRouter ↗ | $0.037 | $0.170 | 471ms | 32 | 100% | API-measured |
| kyma | Pricebook (LiteLLM) ↗ | $0.047 | $0.230 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $0.050 | $0.250 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $0.050 | $0.250 | 562ms | 114 | — | API-measured |
| novita-ai | Novita AI ↗ | $0.050 | $0.250 | — | — | — | API-measured |
| Crusoe (bf16) | OpenRouter ↗ | $0.050 | $0.250 | 206ms | 271 | 100% | API-measured |
| Novita (fp4) | OpenRouter ↗ | $0.050 | $0.250 | 722ms | 140 | 100% | API-measured |
| Mancer 2 (fp8) | OpenRouter ↗ | $0.055 | $0.250 | 773ms | 66 | 100% | API-measured |
| sail | Pricebook (LiteLLM) ↗ | $0.060 | $0.400 | — | — | — | Official list |
| Sail Research (fp4) | OpenRouter ↗ | $0.060 | $0.400 | 712ms | 125 | 100% | API-measured |
| DigitalOcean | OpenRouter ↗ | $0.060 | $0.420 | 689ms | 58 | 100% | API-measured |
| Google (global) | OpenRouter ↗ | $0.090 | $0.360 | 543ms | 36 | — | API-measured |
| ovhcloud | Pricebook (LiteLLM) ↗ | $0.080 | $0.400 | — | — | — | Official list |
| nscale | HuggingFace Router ↗ | $0.100 | $0.400 | 469ms | 121 | — | API-measured |
| ovhcloud | HuggingFace Router ↗ | $0.090 | $0.470 | 423ms | 28 | — | API-measured |
| baseten | Pricebook (LiteLLM) ↗ | $0.100 | $0.500 | — | — | — | Official list |
| baseten | HuggingFace Router ↗ | $0.100 | $0.500 | 162ms | 141 | — | API-measured |
| BaseTen (fp4/us) | OpenRouter ↗ | $0.100 | $0.500 | 249ms | 167 | 100% | API-measured |
| BaseTen (fp4) | OpenRouter ↗ | $0.100 | $0.500 | 339ms | 118 | 100% | 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 |
| nebius | Pricebook (LiteLLM) ↗ | $0.150 | $0.600 | — | — | — | Official list |
| together_ai | 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 |
| zerogpu | Pricebook (LiteLLM) ↗ | $0.150 | $0.600 | — | — | — | Official list |
| aiand | Pricebook (LiteLLM) ↗ | $0.150 | $0.600 | — | — | — | Official list |
| Amazon Bedrock (eu-west-1) | OpenRouter ↗ | $0.150 | $0.600 | 410ms | 182 | 100% | API-measured |
| Nebius (fp4) | OpenRouter ↗ | $0.150 | $0.600 | 282ms | 282 | 100% | API-measured |
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.
| App | Tokens (30d) | Requests |
|---|---|---|
| cvi-magic-tasks-ai-tagging | 45B | 19M |
| Mira | 32B | 4M |
| OP.GG | 26B | 4M |
| LibreChat | 16B | 470K |
| Craft | 12B | 3M |
Volume trend
Last 30 days: 56B → 55B (-3%); range 0–99B 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 (batch) cost?
Cheapest measured offer right now: $0.031/1M input, $0.115/1M output via PrimeIntellect (fp4) — across 41 tracked providers, refreshed hourly.
Who serves gpt-oss-120b (batch)?
41 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 (batch) used?
gpt-oss-120b (batch) routed 55B 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.