GPT OSS 20B
inferenceapis/openai/gpt-oss-20b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.08
Blended $/1M (3:1)
$0.04
Input $/1M
$0.19
Output $/1M
$0.23
1M in + 1M out
—
Cache read $/1M
#821 of 9,232
Cheapest rank
- Provider
- Inference APIs (
inferenceapis) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GPT OSS 20B” is offered by 30 providers — cheapest-effective first. LMStudio is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| LMStudio | free | free | $0.00 | 131k |
| Nvidia | free | free | $0.00 | 131k |
| QVAC | free | free | $0.00 | 131k |
| InferAll | free | free | $0.00 | 131k |
| NanoGPT | $0.018 | $0.09 | $0.04 | 131k |
| Kilo Gateway | $0.018 | $0.09 | $0.04 | 131k |
| OpenRouter | $0.03 | $0.13 | $0.06 | 131k |
| Deep Infra | $0.03 | $0.14 | $0.06 | 131k |
| Vercel AI Gateway | $0.03 | $0.14 | $0.06 | 131k |
| Kenari | $0.036 | $0.1543 | $0.07 | 131k |
| Cortecs | $0.045 | $0.167 | $0.08 | 131k |
| Inference APIs (this) | $0.04 | $0.19 | $0.08 | 131k |
| DevPass (LLM Gateway) | $0.04 | $0.19 | $0.08 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Inference APIs and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-20b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):