| Spec | gpt-oss-120b | DeepSeek V4.1 Flash |
|---|---|---|
| Lowest input | $0.037DeepInfra | $0.12Morph |
| Lowest output | $0.17DeepInfra | $0.42DeepInfra |
| Lowest cached input | Not listed | $0.003Doubleword |
| Context | 131K | 1.05M |
| Max output | 131K | 524K |
| Providers | 2 | 9 |
| Released | August 5, 2025 | September 10, 2026 |
| Weights | Open | Open |
| Lab | OpenAI | DeepSeek |
| Model ID | openai/gpt-oss-120b | deepseek/deepseek-v4.1-flash |
USD per 1M tokens, as of November 5, 2026.
| Provider | gpt-oss-120b | DeepSeek V4.1 Flash |
|---|---|---|
| DeepInfra | $0.037 / $0.17 | $0.14 / $0.42 |
| Doubleword | – | $0.15 / $0.60 |
| Inference.net | – | $0.30 / $1.00 |
| Morph | – | $0.12 / $0.80 |
| Nebius | – | $0.30 / $1.20 |
| Novita AI | – | $0.30 / $1.20 |
| Phala | $0.15 / $0.60 | – |
| RunInfra | – | $0.14 / $0.58 |
| StreamLake | – | $0.30 / $1.20 |
| Wafer | – | $0.19 / $0.65 |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| gpt-oss-120bDeepInfra | $0.16 | $2.70 | $27.00 |
| DeepSeek V4.1 FlashDeepInfra | $0.49 | $9.10 | $91.00 |
On each model's cheapest provider by input plus output list price.
Input: gpt-oss-120b at $0.037 per million input tokens vs $0.12 (DeepSeek V4.1 Flash), 3.2x lower. Output: gpt-oss-120b at $0.17 per million output tokens vs $0.42 (DeepSeek V4.1 Flash), 2.5x lower. Lowest listed prices as of November 5, 2026.
DeepSeek V4.1 Flash, with 1.05M tokens vs 131K.
1 provider serves both: DeepInfra. gpt-oss-120b has 2 providers in total and DeepSeek V4.1 Flash has 9.
No provider lists a cached rate for gpt-oss-120b. DeepSeek V4.1 Flash from $0.003 (Doubleword).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "openai/gpt-oss-120b" to "deepseek/deepseek-v4.1-flash".
