gpt-oss-120b API price
The cheapest host lists gpt-oss-120b at USD 0.03 per 1M input tokens and USD 0.187 output (AkashML, bf16 quantization, inference/openrouter/openai/gpt-oss-120b/akashml/bf16); the median across hosts is USD 0.08. 22 hosts, 2026-10-28 (UTC). Hosts run different quantizations; each row states its own.
List prices, not transacted prices. What that means.
Cheapest gpt-oss-120b input price
Change: 0.0% from 2026-10-22 to 2026-10-28 (like for like, on the constituents both days share).
Dashed lines with a diamond mark days on which the set of constituents (n) changed; a jump on such a day can be coverage, not a price move.
By host
- BaseTen USD 0.10
- Groq USD 0.15
- Together USD 0.15
- SambaNova USD 0.22
- Cerebras USD 0.35
- AkashML USD 0.03
- CoreWeave USD 0.03
- DekaLLM USD 0.03
One line per host, from that listing's own recorded changes; a price holds until the next change.
Hosts with their own price page (first-party)
Hosts publish no quantization on their pages, so it reads unknown.
| SKU | Host | Quantization | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|---|
| inference/baseten/openai/gpt-oss-120b/baseten/unknown | BaseTen | unknown | USD 0.10 | USD 0.50 | 2026-10-27 18:02 UTC | baseten-pricing | ||
| inference/groq/openai/gpt-oss-120b/groq/unknown | Groq | unknown | USD 0.15 | USD 0.60 | 2026-10-27 16:47 UTC | groq-models | ||
| inference/together/openai/gpt-oss-120b/together/unknown | Together | unknown | USD 0.15 | USD 0.60 | 2026-10-28 01:51 UTC | together-pricing | ||
| inference/sambanova/openai/gpt-oss-120b/sambanova/unknown | SambaNova | unknown | USD 0.22 | USD 0.59 | 131,072 | 2026-10-28 07:37 UTC | sambanova-models | |
| inference/cerebras/openai/gpt-oss-120b/cerebras/unknown | Cerebras | unknown | USD 0.35 | USD 0.75 | 131,072 | 2026-10-28 07:37 UTC | cerebras-models |
Hosts via OpenRouter endpoints
The upstream host, its quantization and the price OpenRouter lists for it (a cross-check of the host's own price).
| SKU | Host | Quantization | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|---|
| inference/openrouter/openai/gpt-oss-120b/akashml/bf16 | AkashML | bf16 | USD 0.03 | USD 0.187 | USD 0.03 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/coreweave/fp4 | CoreWeave | fp4 | USD 0.03 | USD 0.17 | USD 0.03 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/dekallm/bf16 | DekaLLM | bf16 | USD 0.03 | USD 0.18 | USD 0.03 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/near-ai/fp4 | Near AI | fp4 | USD 0.03 | USD 0.15 | USD 0.015 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/venice/int4 | Venice | int4 | USD 0.03 | USD 0.15 | USD 0.03 | 128,000 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/deepinfra/bf16 | DeepInfra | bf16 | USD 0.037 | USD 0.17 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/crusoe/bf16 | Crusoe | bf16 | USD 0.05 | USD 0.25 | USD 0.05 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/mancer-2/fp8 | Mancer 2 | fp8 | USD 0.05 | USD 0.25 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/novita/fp4 | Novita | fp4 | USD 0.05 | USD 0.25 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/digitalocean/unknown | DigitalOcean | unknown | USD 0.06 | USD 0.42 | USD 0.012 | 128,000 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/sail-research/fp4 | Sail Research | fp4 | USD 0.06 | USD 0.40 | USD 0.03 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/google/unknown | unknown | USD 0.09 | USD 0.36 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | ||
| inference/openrouter/openai/gpt-oss-120b/baseten/fp4 agrees with BaseTen's own price | BaseTen | fp4 | USD 0.10 | USD 0.50 | USD 0.10 | 128,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/parasail/fp4 | Parasail | fp4 | USD 0.10 | USD 0.75 | USD 0.055 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/sambanova/unknown disagrees with SambaNova's own price: USD 0.22 in / USD 0.59 out (first-party row); the first-party row counts | SambaNova | unknown | USD 0.14 | USD 0.95 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/amazon-bedrock/unknown | Amazon Bedrock | unknown | USD 0.15 | USD 0.60 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/groq/unknown agrees with Groq's own price | Groq | unknown | USD 0.15 | USD 0.60 | USD 0.075 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/mara/unknown | Mara | unknown | USD 0.15 | USD 0.75 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/nebius/fp4 | Nebius | fp4 | USD 0.15 | USD 0.60 | USD 0.10 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/phala/unknown | Phala | unknown | USD 0.15 | USD 0.60 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/siliconflow/fp8 | SiliconFlow | fp8 | USD 0.15 | USD 0.60 | USD 0.075 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
| inference/openrouter/openai/gpt-oss-120b/together/unknown agrees with Together's own price | Together | unknown | USD 0.15 | USD 0.60 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check | |
| inference/openrouter/openai/gpt-oss-120b/cerebras/fp16 agrees with Cerebras's own price | Cerebras | fp16 | USD 0.35 | USD 0.75 | USD 0.35 | 131,072 | 2026-10-27 23:33 UTC | openrouter-endpoints community cross-check |
Other community cross-checks
Not in the cheapest-host series.
| SKU | Host | Quantization | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|---|
| inference/hf-router/openai/gpt-oss-120b/deepinfra/unknown | DeepInfra | unknown | USD 0.037 | USD 0.17 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/novita/unknown | Novita | unknown | USD 0.05 | USD 0.25 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/ovhcloud/unknown | ovhcloud | unknown | USD 0.09 | USD 0.47 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/baseten/unknown | BaseTen | unknown | USD 0.10 | USD 0.50 | 128,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/nscale/unknown | nscale | unknown | USD 0.10 | USD 0.40 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/groq/unknown | Groq | unknown | USD 0.15 | USD 0.75 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | |
| inference/hf-router/openai/gpt-oss-120b/scaleway/unknown | scaleway | unknown | USD 0.171 | USD 0.684 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check | ||
| inference/hf-router/openai/gpt-oss-120b/cerebras/unknown | Cerebras | unknown | USD 0.35 | USD 0.75 | 131,072 | 2026-10-28 07:37 UTC | hf-inference-providers community cross-check |
How this page is built
It reads the latest value of the Cheapest gpt-oss-120b input price index series and the per-provider detail behind it, so the page and the series always agree. Definition: The lowest input price, in USD per million tokens, for gpt-oss-120b among the hosts listing it (OpenRouter endpoints and first-party host price pages), with the host and quantization of the cheapest endpoint stated. Data: JSON · CSV · Atom feed.
Cite this
Free to reuse under CC BY 4.0 with this credit. The numbers are list prices, not transacted prices.
InfraRabbit (2026). gpt-oss-120b API price [data as of 2026-10-28]. https://infrarabbit.com/prices/llm/gpt-oss-120b-price (accessed 2026-10-28). List prices, not transacted prices. CC BY 4.0.
BibTeX
@misc{infrarabbit_llm_gpt_oss_120b_price_2026,
author = {InfraRabbit},
title = {gpt-oss-120b API price},
year = {2026},
howpublished = {\url{https://infrarabbit.com/prices/llm/gpt-oss-120b-price}},
note = {Data as of 2026-10-28; accessed 2026-10-28; list prices, not transacted prices; CC BY 4.0}
}