per 1M tokens
OpenAI: gpt-oss-20b
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...
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Darkbloom | darkbloom/fp8 | fp8 | $0.018/1M | $0.09/1M | 131K | 100% | Live | openrouter-endpoints |
| AkashML | akashml/fp4 | fp4 | $0.02/1M | $0.1/1M | 131K | 100% | Live | openrouter-endpoints |
| CoreWeave | coreweave/fp4 | fp4 | $0.03/1M | $0.13/1M | 131K | 100% | Live | openrouter-endpoints |
| DekaLLM | dekallm/bf16 | bf16 | $0.029/1M | $0.14/1M | 131K | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.03/1M | $0.14/1M | 131K | — | Listed | deepinfra |
| DeepInfra | deepinfra/bf16 | bf16 | $0.03/1M | $0.14/1M | 131K | 100% | Live | openrouter-endpoints |
| Parasail | parasail/fp4 | fp4 | $0.03/1M | $0.15/1M | 131K | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from OpenRouter |
batch | — | $0.035/1M | $0.15/1M | — | — | Listed | amazon-bedrock |
| Amazon Bedrock Price differs from OpenRouter |
flex | — | $0.035/1M | $0.15/1M | — | — | Listed | amazon-bedrock |
| Io Net | — | fp16 | $0.053/1M | $0.166/1M | 64K | — | Listed | ionet |
| OVHcloud | — | — | $0.05/1M | $0.18/1M | 131K | — | Listed | ovh |
| Together | — | — | $0.05/1M | $0.2/1M | 131K | — | Listed | together |
| Amazon Bedrock Price differs from the host list |
amazon-bedrock | — | $0.07/1M | $0.15/1M | 131K | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from the host list |
amazon-bedrock/eu-west-1 | — | $0.07/1M | $0.15/1M | 131K | — | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from OpenRouter |
standard | — | $0.07/1M | $0.3/1M | — | — | Listed | amazon-bedrock |
| Oracle Cloud | — | — | $0.07/1M | $0.3/1M | — | — | Listed | oci-pricelist |
| Groq | groq | — | $0.075/1M | $0.3/1M | 131K | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from OpenRouter |
priority | — | $0.1225/1M | $0.525/1M | — | — | Listed | amazon-bedrock |
| Cloudflare | — | — | $0.2/1M | $0.3/1M | — | — | Listed | cloudflare-pricing |
| Groq | — | — | Not published— | Not published— | 131K | — | Listed | groq |
| Replicate | — | — | Not published— | Not published— | — | — | Listed | replicate |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.04/1M | $0.18/1M | 131K | 77% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.11 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.018/1M | $0.09/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.03 | $0.13 | Not published— |
| 2026-09-16 | token | $0.03 | $0.13 | Not published— |
| 2026-09-17 | token | $0.03 | $0.13 | Not published— |
| 2026-09-18 | token | $0.03 | $0.13 | Not published— |
| 2026-09-19 | token | $0.03 | $0.13 | Not published— |
| 2026-09-20 | token | $0.03 | $0.13 | Not published— |
| 2026-09-21 | token | $0.03 | $0.13 | Not published— |
| 2026-09-22 | token | $0.018 | $0.09 | Not published— |
| 2026-09-23 | token | $0.018 | $0.09 | Not published— |
| 2026-09-24 | token | $0.018 | $0.09 | Not published— |
| 2026-09-25 | token | $0.018 | $0.09 | Not published— |
| 2026-09-26 | token | $0.018 | $0.09 | Not published— |
| 2026-09-27 | token | $0.018 | $0.09 | Not published— |
| 2026-09-28 | token | $0.018 | $0.09 | Not published— |
| 2026-09-29 | token | $0.018 | $0.09 | Not published— |
| 2026-09-30 | token | $0.018 | $0.09 | Not published— |
| 2026-10-01 | token | $0.018 | $0.09 | Not published— |
| 2026-10-02 | token | $0.018 | $0.09 | Not published— |
| 2026-10-03 | token | $0.018 | $0.09 | Not published— |
| 2026-10-04 | token | $0.018 | $0.09 | Not published— |
| 2026-10-05 | token | $0.018 | $0.09 | Not published— |
| 2026-10-06 | token | $0.018 | $0.09 | Not published— |
| 2026-10-07 | token | $0.018 | $0.09 | Not published— |
| 2026-10-08 | token | $0.018 | $0.09 | Not published— |
| 2026-10-09 | token | $0.018 | $0.09 | Not published— |
| 2026-10-10 | token | $0.018 | $0.09 | Not published— |
| 2026-10-11 | token | $0.018 | $0.09 | Not published— |
| 2026-10-12 | token | $0.018 | $0.09 | Not published— |
| 2026-10-13 | token | $0.018 | $0.09 | Not published— |
| 2026-10-14 | token | $0.018 | $0.09 | Not published— |
| 2026-10-15 | token | $0.018 | $0.09 | Not published— |
| 2026-10-16 | token | $0.018 | $0.09 | Not published— |
| 2026-10-17 | token | $0.018 | $0.09 | Not published— |
| 2026-10-18 | token | $0.018 | $0.09 | Not published— |
| 2026-10-19 | token | $0.018 | $0.09 | Not published— |
| 2026-10-20 | token | $0.018 | $0.09 | Not published— |
| 2026-10-21 | token | $0.018 | $0.09 | Not published— |
| 2026-10-22 | token | $0.018 | $0.09 | Not published— |
| 2026-10-23 | token | $0.018 | $0.09 | Not published— |
| 2026-10-24 | token | $0.018 | $0.09 | Not published— |
| 2026-10-25 | token | $0.018 | $0.09 | Not published— |
| 2026-10-26 | token | $0.018 | $0.09 | Not published— |
| 2026-10-27 | token | $0.018 | $0.09 | Not published— |
| 2026-10-28 | token | $0.018 | $0.09 | Not published— |
| 2026-10-29 | token | $0.018 | $0.09 | Not published— |
| 2026-10-30 | token | $0.018 | $0.09 | Not published— |
Alternatives
- @cf/ibm-granite/granite-4.0-h-micro$0.017/1M · Compare
- @cf/pfnet/plamo-embedding-1b$0.019/1M · Compare
- @cf/baai/bge-small-en-v1.5$0.02/1M · Compare
- Amazon: Titan Text Embeddings V2$0.02/1M · Compare
- Decision Small$0.02/1M · Compare
- Inception: Mercury Decide$0.02/1M · Compare
Parameters (20)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id openai/gpt-oss-20b. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-20b","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "openai/gpt-oss-20b",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "openai/gpt-oss-20b", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())