OpenAI: gpt-oss-120b
openai/gpt-oss-120bgpt-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.
Modalities
In / out per 1M$0.15 / $0.60
Context128K
ReleasedAug 5, 2025
Providers
27 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 NEAR AIfp4 | $0.03 | $0.15 | $0.01 | 0.57s | 103 tps | 100% |
| $0.03 | $0.19 | $0.03 | 0.36s | 129 tps | 100% | |
| $0.05 | $0.25 | $0.05 | 0.25s | 339 tps | 100% | |
| $0.06 | $0.40 | $0.03 | 0.51s | 159 tps | 100% | |
 DigitalOcean | $0.06 | $0.42 | $0.01 | 0.61s | 67 tps | 100% |
| $0.10 | $0.75 | $0.06 | 0.31s | 267 tps | 100% | |
 Amazon Bedrockeu-west-1 | $0.15 | $0.60 | Variable | 0.50s | 200 tps | 100% |
| $0.15 | $0.60 | $0.10 | 0.27s | 312 tps | 100% | |
| Amazon Bedrock | $0.15 | $0.60 | Variable | 0.57s | 308 tps | 100% |
| $0.35 | $0.75 | $0.35 | 0.16s | 814 tps | 100% | |
| $0.03 | $0.18 | $0.03 | 0.64s | 61 tps | 99.92% | |
 CoreWeavefp4 | $0.03 | $0.17 | $0.03 | 0.24s | 127 tps | 99.9% |
| $0.15 | $0.60 | Variable | 0.24s | 145 tps | 99.89% | |
| $0.15 | $0.60 | $0.07 | 0.17s | 340 tps | 99.75% | |
| $0.05 | $0.25 | Variable | 0.94s | 56 tps | 99.7% | |
| $0.05 | $0.25 | Variable | 0.68s | 171 tps | 99.57% | |
| $0.14 | $0.95 | Variable | 1.12s | 389 tps | 99.55% | |
 DeepInfra (bf16)us · bf16 | $0.04 | $0.17 | Variable | 0.35s | 36 tps | 99.27% |
| $0.15 | $0.60 | Variable | 1.12s | 106 tps | 99.21% | |
 Basetenfp4 | $0.10 | $0.50 | $0.10 | 1.24s | 97 tps | 99.17% |
| $0.03 | $0.15 | $0.03 | 0.84s | 51 tps | 99.1% | |
| Basetenus · fp4 | $0.10 | $0.50 | $0.10 | 0.16s | 180 tps | 98.34% |
| $0.01 | $0.05 | Variable | 1.03s | 67 tps | 98.02% | |
| $0.15 | $0.75 | Variable | 0.57s | 110 tps | 96.74% | |
 SiliconFlowfp8 | $0.15 | $0.60 | $0.07 | — | — | 91.01% |
| DeepInfra (fp8)us · fp8 | $0.20 | $0.95 | Variable | 1.46s | 59 tps | 78.92% |
 Google Vertexglobal | $0.09 | $0.36 | Variable | 0.40s | 65 tps | 0.93% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves gpt-oss-120b in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what gpt-oss-120b costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.15
per 1M tokens
Output
$0.60
per 1M tokens
Cache read
$0.07
per 1M cached tokens
Included in every pass
gpt-oss-120b is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
CoreWeave DeepInfra (bf16) (us) DekaLLM AkashML Baseten MARA Sail Research Parasail Venice Amazon Bedrock (eu-west-1) Cerebras NEAR AI Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together DeepInfra (fp8) (us) Prime Intellect
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
CoreWeave DeepInfra (bf16) (us) DekaLLM AkashML Baseten MARA Sail Research Parasail Venice Amazon Bedrock (eu-west-1) Cerebras NEAR AI Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together DeepInfra (fp8) (us) Prime Intellect
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.63%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.66%
100% 98% 97% 95%
Oct 31, 6:10 PMNow
Apps
Tools that most often run gpt-oss-120b, by tokens this week.
Activity
2056.6B tokens processed market-wide in the last month.
025.0B50.0B75.0B100.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for gpt-oss-120b?
openai/gpt-oss-120b. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does gpt-oss-120b hold?
131,072 tokens per request, of which up to 65,536 can be the response.
What can it accept and return?
Input: text. Output: text.
What does gpt-oss-120b cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.15 per 1M input tokens and $0.60 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2024. Anything later has to come from your prompt or a tool call.
Who built gpt-oss-120b?
OpenAI, in the gpt family.
Explore
Other models your pass can call.
