Calculate the cost of using gpt-oss-120b from Replicate for your AI applications
Pricing data last updated:
Mode: Chat
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gpt-oss-120b is a chat model from Replicate, one of 40 chat models they offer. It is priced at $0.18 per 1M input tokens and $0.72 per 1M output tokens, ranking 544 out of 2292 chat models by cost and cheaper than 76% of models in this category. gpt-oss-120b supports function calling.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
At $0.18 per 1M input tokens and $0.72 per 1M output tokens, gpt-oss-120b ranks 544 out of 2292 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 76% of models in this category.
gpt-oss-120b is one of 40 Replicate chat models, with support for function calling.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gpt-oss-120b |
|---|---|---|---|---|
| Mistral-7B-Instruct-v0.1 | Anyscale | $0.15 | $0.15 | -17% |
| Mixtral-8x7B-Instruct-v0.1 | Anyscale | $0.15 | $0.15 | -17% |
| gpt-oss-120b | Azure | $0.15 | $0.60 | -17% |
Similar chat models from other providers
No. gpt-oss-120b costs $0.18 per 1M input tokens while Mistral-7B-Instruct-v0.1 costs $0.15 per 1M input tokens, making Mistral-7B-Instruct-v0.1 17% more affordable for input. However, gpt-oss-120b may offer different capabilities or performance characteristics that justify the price difference.
gpt-oss-120b input pricing is $0.18 per 1M tokens, which is 67% below the median of $0.55 for chat models. It ranks 544 out of 2292 chat models by input cost, making it cheaper than 76% of models in this category. For output, it costs $0.72 per 1M tokens compared to the median of $1.50.
Among Replicate's 40 chat models, gpt-oss-120b ranks 14 by input cost.
The most comparable chat models to gpt-oss-120b are: Mistral-7B-Instruct-v0.1 from Anyscale ($0.15/1M input tokens); Mixtral-8x7B-Instruct-v0.1 from Anyscale ($0.15/1M input tokens); gpt-oss-120b from Azure ($0.15/1M input tokens); gpt-5.4-nano from Azure ($0.20/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
You can monitor Replicate service health in real time on the Bifrost Replicate Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
gpt-oss-120b is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.18 and generating 1M output tokens costs $0.72.
