GPT OSS 120 B pricing
Source: litellm · updated 2026-10-30
Short answer: GPT OSS 120 B costs $0.047 per million input tokens and $0.230 per million output tokens. That is a 3:1 blended rate of $0.093 per million tokens, ranking it #59 of 732 tracked models by input price.
Input / 1M
$0.047
Output / 1M
$0.230
Output ÷ input
4.87×
Context window
128,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.047 |
| Output, per 1M tokens | $0.230 |
| Output ÷ input multiple | 4.87× |
| 3:1 blended, per 1M tokens | $0.093 |
| Context window | 128,000 tokens |
| Vendor | kyma |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.047 | $0.058 | $0.105 |
| 10M in / 2.5M out | $0.473 | $0.576 | $1.05 |
| 100M in / 25M out | $4.73 | $5.76 | $10.49 |
Other kyma models
| Model | Input | Output |
|---|---|---|
| Llama 3.3 70 B | $0.135 | $0.432 |
| Gemma 4 31 B | $0.164 | $0.469 |
| GPT-5.6 Luna Pro | $0.270 | $1.62 |
| Qwen 3 Coder | $0.355 | $1.61 |
| Qwen 3.7 Plus | $0.432 | $1.73 |
Compare against
Cheaper alternatives
Next cheaper option: Ternary Bonsai 2.9 B at $0.080 per 1M input tokens. Next step up: Schematron V2 Small at $0.050 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.