OpenAI: gpt-oss-20b
microopenai/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...
AA INDEX9.0
CONTEXT131K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED24 min ago
Input
$0.03 /M
Output
$0.15 /M
Blended (40/60)
$0.10 /M
Cost / IQ
$0.4550 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $0.10/M
High: $0.11/M
Average: $0.10/M
Pricing Variants
Cached Input
$0.01/M
50% cheaper than standard
Batch (async)
$0.08/M
24.7% cheaper than standard
In: $0.02/M · Out: $0.11/M
Provider Comparison
11 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Darkbloom | $0.02 | $0.09 | $0.06 | -40.0% |
| AkashML | $0.02 | $0.10 | $0.07 | -33.3% |
| CoreWeave | $0.03 | $0.13 | $0.09 | -11.8% |
| DekaLLM | $0.03 | $0.14 | $0.10 | -6.3% |
| DeepInfra | $0.03 | $0.14 | $0.10 | -5.9% |
| Parasail | $0.03 | $0.15 | $0.10 | median |
| Amazon Bedrock | $0.07 | $0.15 | $0.12 | +15.7% |
| SiliconFlow | $0.04 | $0.18 | $0.12 | +21.6% |
| OpenRelay | $0.05 | $0.20 | $0.14 | +37.3% |
| $0.07 | $0.25 | $0.18 | +74.5% | |
| Groq | $0.07 | $0.30 | $0.21 | +105.9% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$0.4550/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #438 of 522 micro models
← YOU ARE HERE | OpenAI: gpt-oss-20b
Data Sources
Source
Aggregator & direct provider data
11 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/openai/gpt-oss-20b
# Response (truncated)
{ "model_id": "openai/gpt-oss-20b", "name": "OpenAI: gpt-oss-20b", "blended_price_per_m": 0.102, "sit_adjusted_price": 0.454975 }