Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| DeepInfra | $0.037 | – | $0.17 |
| Phala | $0.15 | – | $0.60 |
USD, as of November 5, 2026. Live prices
gpt-oss-120b API
- 131KContext
- 131KMax output
- $0.037/ $0.17From, per 1M in / out
- 2Providers
Providers
Cost
| Workload | DeepInfra |
|---|---|
| 1,000 chat replies2K in, 500 out each | $0.16 |
| 1,000 agent tasks50K in, 5K out each | $2.70 |
| Monthly batch job500M in, 50M out | $27.00 |
gpt-oss versions
| Model | Released | Context | Lowest input | Lowest output | Providers |
|---|---|---|---|---|---|
| gpt-oss-120bThis pageopenai/gpt-oss-120b | August 5, 2025 | 131K | $0.037 | $0.17 | 2 |
| gpt-oss-20bopenai/gpt-oss-20b | August 5, 2025 | 131K | $0.03 | $0.14 | 1 |
Lowest listed price, USD per 1M tokens, as of November 5, 2026.
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-oss-120b",
"messages": [{ "role": "user", "content": "Hello" }]
}'Compare
FAQ
How much does the gpt-oss-120b API cost?
On RouterPlus, gpt-oss-120b costs $0.037 per million input tokens and $0.17 per million output tokens at DeepInfra, the lowest listed prices and the provider where routing starts. Prices as of November 5, 2026.
Which providers serve gpt-oss-120b?
2 providers serve gpt-oss-120b on RouterPlus: DeepInfra and Phala. By default the router tries them in routing order and fails over before the first byte, never mid-answer.
What is the gpt-oss-120b model ID?
Use "openai/gpt-oss-120b" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.
What is the gpt-oss-120b context window?
131K tokens of context and up to 131K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is gpt-oss-120b open weights?
Yes. OpenAI publishes gpt-oss-120b as an open-weight model, which is why several independent providers can host it.
Do any gpt-oss-120b providers retain prompts?
None of the 2 providers serving gpt-oss-120b on RouterPlus list prompt retention.
Can I reserve capacity for gpt-oss-120b?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.