gpt-oss-20b
by OpenAI · openai/gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
- Input / 1M tokens
- $0.018
- Output / 1M tokens
- $0.09
- Context
- 131K
Specs
| Input price | $0.018 / 1M tokens |
|---|---|
| Output price | $0.09 / 1M tokens |
| Cached input | $0.009 / 1M tokens |
| Context window | 131K tokens |
| Max output | 32.8K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 5, 2025 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
10 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Darkbloom | fp8 | 131K | 32.8K | $0.018 | $0.09 | $0.009 | 100% | 935 ms | 64 tok/s | Normal | |
| AkashML | fp4 | 131K | 118K | $0.02 | $0.10 | — | 100% | 426 ms | 133 tok/s | Normal | |
| CoreWeave | fp4 | 131K | 118K | $0.03 | $0.13 | $0.03 | 100% | 223 ms | 92 tok/s | Normal | |
| DekaLLM | bf16 | 131K | 118K | $0.029 | $0.14 | $0.029 | 100% | 421 ms | 56 tok/s | Normal | |
| DeepInfra | bf16 | 131K | 118K | $0.03 | $0.14 | — | 100% | 273 ms | 105 tok/s | Normal | |
| Parasail | fp4 | 131K | 118K | $0.03 | $0.15 | $0.02 | 100% | 1.07 s | 97 tok/s | Normal | |
| Amazon Bedrock | — | 131K | 118K | $0.07 | $0.15 | — | 100% | 325 ms | 113 tok/s | Normal | |
| Amazon Bedrock | — | 131K | 118K | $0.07 | $0.15 | — | 100% | 394 ms | 427 tok/s | Normal | |
| SiliconFlow | fp8 | 131K | 8.19K | $0.04 | $0.18 | — | 86.2% | 1.14 s | 36 tok/s | Code -2 | |
| Groq | — | 131K | 65.5K | $0.075 | $0.30 | $0.0375 | 100% | 398 ms | 396 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- OpenAI
GPT-6 Luna
- Input
- $0.10
- Output
- $0.50
- Context
- 1.05M
- OpenAI
GPT-6.1 Sol
- Input
- $2.00
- Output
- $10.00
- Context
- 1.05M
- OpenAI
GPT-5.6 Luna
- Input
- $0.20
- Output
- $1.20
- Context
- 1.05M
- OpenAI
GPT-6.1 Terra
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M
- OpenAI
GPT-6 Luna Pro
- Input
- $0.10
- Output
- $0.50
- Context
- 1.05M
- OpenAI
GPT-6 Astra
- Input
- $10.00
- Output
- $50.00
- Context
- 1.05M