OpenAI: gpt-oss-120b
microopenai/gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
AA INDEX11.6
CONTEXT131K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED2 min ago
Input
$0.13 /M
Output
$0.60 /M
Blended (40/60)
$0.42 /M
Cost / IQ
$1.4479 /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: $0.38/M
High: $0.42/M
Average: $0.42/M
Pricing Variants
Cached Input
$0.07/M
50% cheaper than standard
Batch (async)
$0.09/M
77.8% cheaper than standard
In: $0.03/M · Out: $0.14/M
Provider Comparison
23 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓CoreWeave | $0.03 | $0.17 | $0.11 | -72.9% |
| DeepInfra | $0.04 | $0.17 | $0.12 | -72.2% |
| DekaLLM | $0.03 | $0.18 | $0.12 | -71.4% |
| AkashML | $0.03 | $0.19 | $0.13 | -70.1% |
| Crusoe | $0.05 | $0.25 | $0.17 | -59.5% |
| Novita | $0.05 | $0.25 | $0.17 | -59.5% |
| Mancer 2 | $0.05 | $0.30 | $0.20 | -52.4% |
| Venice | $0.07 | $0.30 | $0.21 | -50.5% |
| $0.09 | $0.36 | $0.25 | -40.0% | |
| DigitalOcean | $0.06 | $0.42 | $0.28 | -34.3% |
| BaseTen | $0.10 | $0.50 | $0.34 | -19.0% |
| Amazon Bedrock | $0.15 | $0.60 | $0.42 | median |
| Fireworks | $0.15 | $0.60 | $0.42 | median |
| Groq | $0.15 | $0.60 | $0.42 | median |
| Nebius | $0.15 | $0.60 | $0.42 | median |
| OpenRelay | $0.15 | $0.60 | $0.42 | median |
| Phala | $0.15 | $0.60 | $0.42 | median |
| SiliconFlow | $0.15 | $0.60 | $0.42 | median |
| Together | $0.15 | $0.60 | $0.42 | median |
| Parasail | $0.10 | $0.75 | $0.49 | +16.7% |
| Mara | $0.15 | $0.75 | $0.51 | +21.4% |
| Cerebras | $0.35 | $0.75 | $0.59 | +40.5% |
| SambaNova | $0.14 | $0.95 | $0.63 | +49.0% |
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)$1.4479/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 #437 of 581 micro models
← YOU ARE HERE | OpenAI: gpt-oss-120b
Data Sources
Source
Aggregator & direct provider data
23 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/openai/gpt-oss-120b
# Response (truncated)
{ "model_id": "openai/gpt-oss-120b", "name": "OpenAI: gpt-oss-120b", "blended_price_per_m": 0.42, "sit_adjusted_price": 1.447921 }