OpenAI

gpt-oss-120b

OpenAI's open-weight 120B reasoning model, available across multiple inference gateways with configurable reasoning effort.

ActiveReleased August 5, 2025Knowledge cutoff June 1, 2024Available from 28 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: OpenAI models, OpenAI pricing, Prompt caching (1,024 minimum, 30m TTL)

Price per 1M tokens
$0.15 in / $0.6 out
Context window131,072
Max output131,072
Batch discount-50%
Input
  • Text
Output
  • Text
Priced across28 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRateBatch
Input$0.15 / M$0.075 / M
Output$0.6 / M$0.3 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$66.00
at current list prices
Fresh input$30.00
Output incl. thinking$36.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformRegionInput / MOutput / MCache read / MBatchAccess
Together AI
-$0.15$0.6-✓Direct
OpeninferenceLowest
-$0.03$0.15--via OpenRouter
Wandb
-$0.04$0.14$0.04-via OpenRouter
Coreweave
-$0.03$0.17$0.03-via OpenRouter
DeepInfra
-$0.037$0.17--via OpenRouter
Dekallm
-$0.03$0.18$0.03-via OpenRouter
Akashml
-$0.037$0.187$0.037-via OpenRouter
Crusoe
-$0.05$0.25$0.05-via OpenRouter
Novita
-$0.05$0.25--via OpenRouter
Mancer-2
-$0.045$0.275--via OpenRouter
Google
-$0.09$0.36--via OpenRouter
DigitalOcean
-$0.06$0.42$0.012-via OpenRouter
SiliconFlow
-$0.05$0.45--via OpenRouter
Baseten
-$0.1$0.5$0.1-via OpenRouter
AWS Bedrock
$0.15$0.6-✓Direct
Azure AI Foundry
-$0.15$0.6--Direct
Fireworks AI
-$0.15$0.6$0.015✓Direct
AWS Bedrock
-$0.15$0.6--via OpenRouter
Groq
-$0.15$0.6$0.075-via OpenRouter
Nebius
-$0.15$0.6--via OpenRouter
Phala
-$0.15$0.6--via OpenRouter
Together AI
-$0.15$0.6--via OpenRouter
Azure AI Foundry (Fireworks)
-$0.165$0.66$0.082-Direct
Azure AI Foundry · Data zone
-$0.165$0.66--Direct
Parasail
-$0.1$0.75$0.055-via OpenRouter
Mara
-$0.15$0.75--via OpenRouter
SambaNova
-$0.14$0.95--via OpenRouter
Cerebras
-$0.35$0.75$0.35-via OpenRouter

Some hosts price by region. Shown rates match the selected region.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.15 / $0.6 per 1M since May 21, 2026.

More from OpenAI

Other models from the same provider.

GPT-6.1 Sol
openai/gpt-6.1-sol
$2 / $10 in / out per 1M
GPT-6 Sol
openai/gpt-6-sol
$2 / $10 in / out per 1M
GPT-6 Luna
openai/gpt-6-luna
$0.1 / $0.5 in / out per 1M
GPT-6 Astra
openai/gpt-6-astra
$10 / $50 in / out per 1M
GPT-5.6 Sol
openai/gpt-5.6-sol
$4 / $20 in / out per 1M
GPT-5.6 Terra
openai/gpt-5.6-terra
$2 / $12 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every gpt-oss-120b call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.