Last refreshed 2026-04-19. Next refresh: weekly.
Why use gpt-oss-20b on Fireworks AI?
Fireworks AI offers gpt-oss-20b with pay-as-you-go pricing at $0.07/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Compare gpt-oss-20b across 12 providers to find the best fit for your use caseInput / 1M
$0.070
Output / 1M
$0.30
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export FIREWORKS_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],Model ID
accounts/fireworks/models/gpt-oss-20bRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/gpt-oss-20b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "accounts/fireworks/models/gpt-oss-20b", not the LLMReference slug "gpt-oss-20b".
- Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
- The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.
Compare gpt-oss-20b Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.20 | $0.30 |
| OpenRouter | $0.03 | $0.14 |
| Fireworks AI | $0.07 | $0.30 |
| GCP Vertex AI | $0.07 | $0.25 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.07 |
| Output tokens | $0.30 |
Capabilities
JSON / Tool useStructured Outputs
About gpt-oss-20b
OpenAI open-weight model with 20 billion parameters. Lightweight, efficient text-only model with reasoning and function calling. Free for self-hosting. Released August 5, 2025.
Get Started
Model Specs
Released2025-08-05
Parameters20B
Context131k
ArchitectureDecoder Only
Knowledge cutoff2025-08