Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
gpt-oss-20bA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| gpt-oss-20b | |
|---|---|
| Input per 1M | $0.018 |
| Output per 1M | $0.09 |
| Cached input | n/a |
| Batch in / out | n/a |
| Blended (3:1) | $0.036 |
| Context | 131K |
| Routes | 12 |
| Released | Aug 5, 2025 |
| Leadersboard score | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
gpt-oss-20b
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Darkbloom fp8 | $0.018 | $0.09 | $0.018 / $0.09Same as list | n/a | Same as list |
| AkashML fp4 | $0.02 | $0.1 | $0.02 / $0.1+11% vs list | n/a | +11% vs list |
 CoreWeavefp4 · cached $0.03 | $0.03 | $0.13 | $0.03 / $0.13+53% vs list | $0.03 | +53% vs list |
| DekaLLM bf16 | $0.029 | $0.14 | $0.029 / $0.14+58% vs list | n/a | +58% vs list |
 DeepInfrabf16 | $0.03 | $0.14 | $0.03 / $0.14+60% vs list | n/a | +60% vs list |
 Parasailfp4 · cached $0.02 | $0.03 | $0.15 | $0.03 / $0.15+67% vs list | $0.02 | +67% vs list |
 Novita AIfp4 | $0.04 | $0.15 | $0.04 / $0.15+88% vs list | n/a | +88% vs list |
 SiliconFlowfp8 | $0.04 | $0.18 | $0.04 / $0.18+108% vs list | n/a | +108% vs list |
 AWS BedrockDefault region | $0.07 | $0.15 | $0.07 / $0.15+150% vs list | n/a | +150% vs list |
| AWS Bedrock eu-west-1 | $0.07 | $0.15 | $0.07 / $0.15+150% vs list | n/a | +150% vs list |
 Google Vertex AIus-central1 | $0.07 | $0.25 | $0.07 / $0.25+219% vs list | n/a | +219% vs list |
 GroqDefault region · cached $0.037 | $0.075 | $0.3 | $0.075 / $0.3+265% vs list | $0.037 | +265% vs list |
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.