Pricingby Glyphgpt-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.
Ways to buy 29
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| PrimeIntellect fp4 | $0.01 | $0.037 | $0.01 / $0.037Cheapest | n/a | Cheapest |
| Near AI fp4 · cached $0.015 | $0.03 | $0.15 | $0.03 / $0.15+258% vs cheapest | $0.015 | +258% vs cheapest |
int4 · cached $0.03 | $0.03 | $0.15 | $0.03 / $0.15+258% vs cheapest | $0.03 | +258% vs cheapest |
fp4 · cached $0.03 | $0.03 | $0.17 | $0.03 / $0.17+288% vs cheapest | $0.03 | +288% vs cheapest |
| DekaLLM bf16 · cached $0.03 | $0.03 | $0.18 | $0.03 / $0.18+303% vs cheapest | $0.03 | +303% vs cheapest |
| AkashML fp4 · cached $0.03 | $0.03 | $0.187 | $0.03 / $0.187+313% vs cheapest | $0.03 | +313% vs cheapest |
bf16 | $0.037 | $0.17 | $0.037 / $0.17+319% vs cheapest | n/a | +319% vs cheapest |
bf16 · cached $0.05 | $0.05 | $0.25 | $0.05 / $0.25+497% vs cheapest | $0.05 | +497% vs cheapest |
| Mancer 2 fp8 | $0.045 | $0.275 | $0.045 / $0.275+512% vs cheapest | n/a | +512% vs cheapest |
| Sail Research fp4 · cached $0.03 | $0.06 | $0.4 | $0.06 / $0.4+766% vs cheapest | $0.03 | +766% vs cheapest |
Default region · cached $0.012 | $0.06 | $0.42 | $0.06 / $0.42+796% vs cheapest | $0.012 | +796% vs cheapest |
global | $0.09 | $0.36 | $0.09 / $0.36+840% vs cheapest | n/a | +840% vs cheapest |
fp4 · cached $0.1 | $0.1 | $0.5 | $0.1 / $0.5+1094% vs cheapest | $0.1 | +1094% vs cheapest |
fp4-us, fp4 · cached $0.1 | $0.1 | $0.5 | $0.1 / $0.5+1094% vs cheapest | $0.1 | +1094% vs cheapest |
 AWS BedrockDefault region | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
| AWS Bedrock eu-west-1 | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
From the platform pricing page | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
Default region · cached $0.075 | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | $0.075 | +1467% vs cheapest |
fp4 · cached $0.1 | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | $0.1 | +1467% vs cheapest |
From the platform pricing page | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
| Phala Default region | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
fp8 · cached $0.075 | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | $0.075 | +1467% vs cheapest |
Default region | $0.15 | $0.6 | $0.15 / $0.6+1467% vs cheapest | n/a | +1467% vs cheapest |
fp4 · cached $0.055 | $0.1 | $0.75 | $0.1 / $0.75+1467% vs cheapest | $0.055 | +1467% vs cheapest |
From the platform pricing page | $0.159 | $0.636 | $0.159 / $0.636+1561% vs cheapest | n/a | +1561% vs cheapest |
fast, fp4 | $0.15 | $0.75 | $0.15 / $0.75+1691% vs cheapest | n/a | +1691% vs cheapest |
Default region | $0.14 | $0.95 | $0.14 / $0.95+1945% vs cheapest | n/a | +1945% vs cheapest |
fp8 | $0.2 | $0.95 | $0.2 / $0.95+2213% vs cheapest | n/a | +2213% vs cheapest |
fp16 · cached $0.35 | $0.35 | $0.75 | $0.35 / $0.75+2587% vs cheapest | $0.35 | +2587% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $1.74 direct.
Helicone$1.74+0%
Kong AI Gateway$1.74+0%
LiteLLM$1.74+0%
Neon AI Gateway$1.74+0%
Vercel AI Gateway$1.74+0%
Requesty$1.83+5%
Eden AI$1.84+5.5%
OpenRouter$1.84+5.5%
Cloudflare AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. |
 Titan Text Embeddings V2Amazon Nova · 8K | $0.02 | Free | $0.02 / Free | $0.015 | 8K | Lab list price | · | Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. |
Perplexity · 32K | $0.03 | Free | $0.03 / Free | $0.022 | 32K | Lab list price | · | pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. |
Qwen (Alibaba) · 33K | $0.02 | Free | $0.02 / Free | $0.015 | 33K | on DeepInfra (us) | · | The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. |
Qwen (Alibaba) · 41K | $0.01 | Free | $0.01 / Free | $0.0075 | 41K | on DeepInfra (us) | · | The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. |
About gpt-oss-120b
Takes text in and returns text. First listed Sep 23, 2026. Up to 66K output tokens. Blended price $0.017 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?
$0.01 per million input tokens and $0.037 per million output tokens.
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 29 routes tracked, PrimeIntellect is cheapest at $0.01 input and $0.037 output per million tokens.
Has gpt-oss-120b's price changed?
Yes. The output price went from $0.3 to $0.275, first seen Oct 2, 2026.