API pricing per million tokens
gpt-oss-20b Open weightsChecked 7h ago
- Input
- $0.018
- per 1M, Darkbloom (fp8)
- Output
- $0.09
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 131K
- 33K max output
Where to buy it (12)
- Darkbloomfp8, fp8$0.018 / $0.09$0.036 blended
- AkashMLfp4, fp4$0.02 / $0.1$0.04 blended
CoreWeavefp4, fp4$0.03 / $0.13cached $0.03
- DekaLLMbf16, bf16$0.029 / $0.14$0.057 blended
DeepInfrabf16, bf16$0.03 / $0.14$0.058 blended
Parasailfp4, fp4$0.03 / $0.15cached $0.02
Novita AIfp4, fp4$0.04 / $0.15$0.068 blended
SiliconFlowfp8, fp8$0.04 / $0.18$0.075 blended
AWS Bedrockdefault region$0.07 / $0.15$0.09 blended
AWS Bedrockeu-west-1$0.07 / $0.15$0.09 blended
Google Vertex AIus-central1$0.07 / $0.25$0.115 blended
Groqdefault region$0.075 / $0.3cached $0.037
Through a gateway
Your own numbers100M input and 20M output tokens a month: $3.60 direct.
Helicone$3.60+0%
Kong AI Gateway$3.60+0%
LiteLLM$3.60+0%
Vercel AI Gateway$3.60+0%
AWS Bedrock$3.60+0%
Azure AI Foundry$3.60+0%
Google Vertex AI$3.60+0%
Databricks Mosaic AI$3.60+0%
Hugging Face Inference$3.60+0%
Cloudflare AI Gateway$3.78+5%
Requesty$3.78+5%
Eden AI$3.80+5.5%
OpenRouter$3.80+5.5%
Snowflake Cortex AI$4.32+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
BigQuery MLn/a
Cloudflare Workers AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
GPT-6 LunaOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
GPT-6 Luna ProOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
GPT-6 SolOpenAI · 1.05M$2 / $10in / out per 1M$2$10$0.21.05MSep 22, 2026
GPT-6 Sol ProOpenAI · 1.05M$2 / $10in / out per 1M$2$10$0.21.05MSep 22, 2026
GLM 5.3 FlashZ.ai · via InferenceNet (fp4) · 1.31M$0.045 / $0.14in / out per 1M$0.045$0.14$0.011.31MAug 26, 2026
DeepSeek V4 Flash 0731DeepSeek · via StreamLake (fp8) · 1.31M$0.053 / $0.158in / out per 1M$0.053$0.158$0.00171.31MJul 31, 2026
Qwen3.7 FlashQwen (Alibaba) · 1M$0.03 / $0.13in / out per 1M$0.03$0.13$0.0061MJul 27, 2026
Mistral Embed 2312Mistral AI · 8K$0.1 / Freein / out per 1M$0.1Freen/a8KOct 31, 2025
About gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.036 per 1M tokens at 3 input to 1 output.
Questions
How much does gpt-oss-20b cost?
$0.018 per million input tokens and $0.09 per million output tokens.
What is the context window of gpt-oss-20b?
131K tokens, with up to 33K tokens of output.
Where is gpt-oss-20b cheapest?
Of 12 routes tracked, Darkbloom is cheapest at $0.018 input and $0.09 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.