| Spec | gpt-oss-120b | Qwen3.8 27B |
|---|---|---|
| Lowest input | $0.037DeepInfra | $0.039Chutes |
| Lowest output | $0.17DeepInfra | $0.40RunInfra |
| Lowest cached input | Not listed | $0.0039Chutes |
| Context | 131K | 262K |
| Max output | 131K | 262K |
| Providers | 2 | 8 |
| Released | August 5, 2025 | August 13, 2026 |
| Weights | Open | Open |
| Lab | OpenAI | Qwen |
| Model ID | openai/gpt-oss-120b | qwen/qwen3.8-27b |
USD per 1M tokens, as of November 5, 2026.
| Provider | gpt-oss-120b | Qwen3.8 27B |
|---|---|---|
| Phala | $0.15 / $0.60 | $0.20 / $2.50 |
| Chutes | – | $0.039 / $1.25 |
| DeepInfra | $0.037 / $0.17 | – |
| Doubleword | – | $0.45 / $3.00 |
| Munito AI | – | $0.18 / $2.40 |
| Nebius | – | $0.45 / $3.00 |
| RunInfra | – | $0.10 / $0.40 |
| StreamLake | – | $0.50 / $3.00 |
| Wafer | – | $0.06 / $2.30 |
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 |
| Qwen3.8 27BRunInfra | $0.40 | $7.00 | $70.00 |
On each model's cheapest provider by input plus output list price.
Input: gpt-oss-120b at $0.037 per million input tokens vs $0.039 (Qwen3.8 27B), 5% lower. Output: gpt-oss-120b at $0.17 per million output tokens vs $0.40 (Qwen3.8 27B), 2.4x lower. Lowest listed prices as of November 5, 2026.
Qwen3.8 27B, with 262K tokens vs 131K.
1 provider serves both: Phala. gpt-oss-120b has 2 providers in total and Qwen3.8 27B has 8.
No provider lists a cached rate for gpt-oss-120b. Qwen3.8 27B from $0.0039 (Chutes).
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 "qwen/qwen3.8-27b".
