gpt-oss-120b
- Input / output
- $0.03 / $0.15
- Providers
- 22
- Spread
- 6.9×
- 7 days
- +16.5%
- 30 days
- 0%
- Context
- 128K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
Near AICheapest fp4 | $0.03 | $0.15 | $0.06 | −7.7% | |||
| int4 | $0.03 | $0.15 | $0.06 | −7.7% | |||
| fp4 | $0.03 | $0.17 | $0.065 | ref | |||
| bf16 | $0.03 | $0.18 | $0.0675 | +3.8% | |||
| fp4 | $0.03 | $0.187 | $0.0693 | +6.5% | |||
| bf16 | $0.037 | $0.17 | $0.0703 | +8.1% | |||
| bf16 | $0.05 | $0.25 | $0.10 | +54% | |||
| fp4 | $0.06 | $0.40 | $0.145 | +123% | |||
| $0.06 | $0.42 | $0.15 | +131% | ||||
Googleglobal | $0.09 | $0.36 | $0.158 | +142% | |||
| fp8 | $0.085 | $0.375 | $0.158 | +142% | |||
| fp4 | $0.10 | $0.50 | $0.20 | +208% | |||
BaseTenfp4/us fp4 | $0.10 | $0.50 | $0.20 | +208% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
| $0.15 | $0.60 | $0.263 | +304% | ||||
Amazon Bedrockeu-west-1 | $0.15 | $0.60 | $0.263 | +304% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
| fp4 | $0.15 | $0.60 | $0.263 | +304% | |||
| fp4 | $0.10 | $0.75 | $0.263 | +304% | |||
| fp8 | $0.15 | $0.60 | $0.263 | +304% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
Parasailfast fp4 | $0.15 | $0.75 | $0.30 | +362% | |||
| $0.14 | $0.95 | $0.343 | +427% | ||||
| fp4 | $0.308 | $0.661 | $0.396 | +510% | |||
| fp16 | $0.35 | $0.75 | $0.45 | +592% |
- Near AICheapest$0.06$0.03 in · $0.15 out−7.7% vs ref128K ctx99.9% uptimefp4
- $0.06$0.03 in · $0.15 out−7.7% vs ref125K ctx100% uptimeint4
- $0.065$0.03 in · $0.17 outref vs ref128K ctx98.9% uptimefp4
- $0.0675$0.03 in · $0.18 out+3.8% vs ref128K ctx96.5% uptimebf16
- $0.0693$0.03 in · $0.187 out+6.5% vs ref128K ctx100% uptimefp4
- $0.0703$0.037 in · $0.17 out+8.1% vs ref128K ctx43.5% uptimebf16
- $0.10$0.05 in · $0.25 out+54% vs ref128K ctx100% uptimebf16
- $0.145$0.06 in · $0.40 out+123% vs ref128K ctx100% uptimefp4
- $0.15$0.06 in · $0.42 out+131% vs ref125K ctx100% uptime
- global$0.158$0.09 in · $0.36 out+142% vs ref128K ctx99.7% uptime
- $0.158$0.085 in · $0.375 out+142% vs ref128K ctx97.5% uptimefp8
- $0.20$0.10 in · $0.50 out+208% vs ref128K ctx100% uptimefp4
- fp4/us$0.20$0.10 in · $0.50 out+208% vs ref128K ctx99.9% uptimefp4
- $0.263$0.15 in · $0.60 out+304% vs ref
- $0.263$0.15 in · $0.60 out+304% vs ref128K ctx100% uptime
- eu-west-1$0.263$0.15 in · $0.60 out+304% vs ref128K ctx99.9% uptime
- $0.263$0.15 in · $0.60 out+304% vs ref128K ctx99.6% uptime
- $0.263$0.15 in · $0.60 out+304% vs ref128K ctx100% uptimefp4
- $0.263$0.10 in · $0.75 out+304% vs ref128K ctx100% uptimefp4
- $0.263$0.15 in · $0.60 out+304% vs ref128K ctx88.2% uptimefp8
- $0.263$0.15 in · $0.60 out+304% vs ref128K ctx99.9% uptime
- fast$0.30$0.15 in · $0.75 out+362% vs ref128K ctx100% uptimefp4
- $0.343$0.14 in · $0.95 out+427% vs ref128K ctx98.6% uptime
- $0.396$0.308 in · $0.661 out+510% vs ref128K ctx98.4% uptimefp4
- $0.45$0.35 in · $0.75 out+592% vs ref128K ctx100% uptimefp16
Blended = (3 × input + output) / 4. Ref $0.065 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Near AI, Logit | $0.015 |
| Venice, CoreWeave +3 | $0.03 |
| DeepInfra | $0.0185 |
| Crusoe | $0.05 |
| DigitalOcean | $0.012 |
| Mancer 2 | $0.085 |
| BaseTen, BaseTen (fp4/us) +1 | $0.10 |
| Groq, SiliconFlow | $0.075 |
| Parasail | $0.055 |
| PrimeIntellect | $0.278 |
| Cerebras | $0.35 |
Changes
- PriceCache read price,$0.315→$0.278−11.7%
- PriceOutput price,$0.75→$0.661−11.9%
- PriceInput price,$0.35→$0.308−12.0%
- PriceCache read price,$0.095→$0.085−10.5%
- PriceInput price,$0.095→$0.085−10.5%
- PriceCache read price,$0.266→$0.315+18.4%
- PriceOutput price,$0.634→$0.75+18.3%
- PriceInput price,$0.296→$0.35+18.2%
- PriceCache read price,$0.315→$0.266−15.6%
- PriceOutput price,$0.75→$0.634−15.5%
- PriceInput price,$0.35→$0.296−15.4%
- PriceCache read price,$0.123→$0.315+156%
- PriceOutput price,$0.293→$0.75+156%
- PriceInput price,$0.137→$0.35+155%
- PriceCache read price,$0.069→$0.123+78.3%
About
The cheapest provider for gpt-oss-120b is Near AI at $0.06 per 1M tokens (blended), charging $0.03 per 1M input and $0.15 per 1M output tokens. 22 providers serve it; the most expensive charges 6.9× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.
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...
- Released
- Aug 5, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- openai/gpt-oss-120b
- Weights
- openai/gpt-oss-120b