Ways to buy 26
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| AkashML bf16 · cached $0.03 | $0.03 | $0.17 | $0.03 / $0.17Cheapest | $0.03 | Cheapest |
 CoreWeavefp4 · cached $0.03 | $0.03 | $0.17 | $0.03 / $0.17Cheapest | $0.03 | Cheapest |
| DekaLLM bf16 | $0.03 | $0.18 | $0.03 / $0.18+4% vs cheapest | n/a | +4% vs cheapest |
 DeepInfrabf16 | $0.037 | $0.17 | $0.037 / $0.17+8% vs cheapest | n/a | +8% vs cheapest |
 Crusoebf16 · cached $0.05 | $0.05 | $0.25 | $0.05 / $0.25+54% vs cheapest | $0.05 | +54% vs cheapest |
 Novita AIfp4 | $0.05 | $0.25 | $0.05 / $0.25+54% vs cheapest | n/a | +54% vs cheapest |
| Mancer 2 fp8 | $0.05 | $0.3 | $0.05 / $0.3+73% vs cheapest | n/a | +73% vs cheapest |
 DigitalOceanDefault region · cached $0.012 | $0.06 | $0.42 | $0.06 / $0.42+131% vs cheapest | $0.012 | +131% vs cheapest |
 Google Vertex AIglobal | $0.09 | $0.36 | $0.09 / $0.36+142% vs cheapest | n/a | +142% vs cheapest |
 Basetenfp4 · cached $0.1 | $0.1 | $0.5 | $0.1 / $0.5+208% vs cheapest | $0.1 | +208% vs cheapest |
 AWS BedrockDefault region | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
| AWS Bedrock eu-west-1 | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
 Databricks Mosaic AI Gateway + Foundation Model APIsFrom the platform pricing page | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
| DeepInfra turbo, bf16 | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
 GroqDefault region · cached $0.075 | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | $0.075 | +304% vs cheapest |
 Nebiusfp4 | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
 OCI Generative AIFrom the platform pricing page | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
| Phala Default region | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
 SiliconFlowfp8 · cached $0.075 | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | $0.075 | +304% vs cheapest |
 Together AIDefault region | $0.15 | $0.6 | $0.15 / $0.6+304% vs cheapest | n/a | +304% vs cheapest |
 Parasailfp4 · cached $0.055 | $0.1 | $0.75 | $0.1 / $0.75+304% vs cheapest | $0.055 | +304% vs cheapest |
 IBM watsonx.aiFrom the platform pricing page | $0.159 | $0.636 | $0.159 / $0.636+328% vs cheapest | n/a | +328% vs cheapest |
| Mara Default region | $0.15 | $0.75 | $0.15 / $0.75+362% vs cheapest | n/a | +362% vs cheapest |
 SambaNovaDefault region | $0.14 | $0.95 | $0.14 / $0.95+427% vs cheapest | n/a | +427% vs cheapest |
| DeepInfra fp8 | $0.2 | $0.95 | $0.2 / $0.95+496% vs cheapest | n/a | +496% vs cheapest |
 Cerebrasfp16 · cached $0.35 | $0.35 | $0.75 | $0.35 / $0.75+592% vs cheapest | $0.35 | +592% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $6.40 direct.
Helicone$6.40+0%
Kong AI Gateway$6.40+0%
LiteLLM$6.40+0%
Vercel AI Gateway$6.40+0%
Cloudflare AI Gateway$6.72+5%
Requesty$6.72+5%
Eden AI$6.75+5.5%
OpenRouter$6.75+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
 GPT-6 LunaOpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Luna Pro OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Sol OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
| GPT-6 Sol Pro OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 Muse Spark 1.3 ContributorMeta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
 GLM 5.3 FlashZ.ai · 1.31M | $0.045 | $0.14 | $0.045 / $0.14 | $0.069 | 1.31M | on InferenceNet (fp4) | · |
| Muse Spark 1.2 Contributor Meta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
 DeepSeek V4 Flash 0731DeepSeek · 1.31M | $0.053 | $0.158 | $0.053 / $0.158 | $0.079 | 1.31M | on StreamLake (fp8) | · |
About gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
Takes text in and returns text. First listed Sep 23, 2026. Up to 66K output tokens. Blended price $0.065 per 1M tokens at 3 input to 1 output. Model id gpt-oss-120b.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does gpt-oss-120b cost?
$0.03 per million input tokens and $0.17 per million output tokens, with cached input at $0.03.
What is the context window of gpt-oss-120b?
131K tokens, with up to 66K tokens of output.
Where is gpt-oss-120b cheapest?
Of 26 routes tracked, AkashML is cheapest at $0.03 input and $0.17 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.