Pricingby Glyphgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Ways to buy 11
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| PrimeIntellect fp4 · cached $0.003 | $0.004 | $0.017 | $0.004 / $0.017Cheapest | $0.003 | Cheapest |
| Darkbloom fp8 · cached $0.009 | $0.018 | $0.09 | $0.018 / $0.09+397% vs cheapest | $0.009 | +397% vs cheapest |
| AkashML fp4 | $0.02 | $0.1 | $0.02 / $0.1+452% vs cheapest | n/a | +452% vs cheapest |
fp4 · cached $0.03 | $0.03 | $0.13 | $0.03 / $0.13+659% vs cheapest | $0.03 | +659% vs cheapest |
| DekaLLM bf16 · cached $0.029 | $0.029 | $0.14 | $0.029 / $0.14+683% vs cheapest | $0.029 | +683% vs cheapest |
bf16 | $0.03 | $0.14 | $0.03 / $0.14+693% vs cheapest | n/a | +693% vs cheapest |
fp4 · cached $0.02 | $0.03 | $0.15 | $0.03 / $0.15+728% vs cheapest | $0.02 | +728% vs cheapest |
fp8 | $0.04 | $0.18 | $0.04 / $0.18+934% vs cheapest | n/a | +934% vs cheapest |
 AWS BedrockDefault region | $0.07 | $0.15 | $0.07 / $0.15+1141% vs cheapest | n/a | +1141% vs cheapest |
| AWS Bedrock eu-west-1 | $0.07 | $0.15 | $0.07 / $0.15+1141% vs cheapest | n/a | +1141% vs cheapest |
Default region · cached $0.037 | $0.075 | $0.3 | $0.075 / $0.3+1710% vs cheapest | $0.037 | +1710% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $0.74 direct.
Helicone$0.74+0%
Kong AI Gateway$0.74+0%
LiteLLM$0.74+0%
Neon AI Gateway$0.74+0%
Vercel AI Gateway$0.74+0%
Requesty$0.78+5%
Eden AI$0.78+5.5%
OpenRouter$0.78+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. |
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-20b
Takes text in and returns text. First listed Sep 23, 2026. Up to 118K output tokens. Blended price $0.0073 per 1M tokens at 3 input to 1 output. Model id gpt-oss-20b.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does gpt-oss-20b cost?
$0.004 per million input tokens and $0.017 per million output tokens, with cached input at $0.003.
What is the context window of gpt-oss-20b?
131K tokens, with up to 118K tokens of output.
Where is gpt-oss-20b cheapest?
Of 11 routes tracked, PrimeIntellect is cheapest at $0.004 input and $0.017 output per million tokens.