Choose a model to open its comparison page.
GPT-OSS API pricing covers 356 API providers, from $0.000007/M to $495.00/M. GPT-OSS free API options are available from 28 providers. The page also shows measured API speed and first-token latency.
GPT-OSS is an open-weight language model family designed for self-hosted inference, research, and cost-efficient alternatives to proprietary GPT-class models.
Input and output token limits for this model, plus how it ranks on long-context understanding.
Compare GPT-OSS API pricing across 328 providers. Prices range from $0.000007/M to $495.00/M. OAI2API offers the lowest rate at $0.000007/M. 28 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-oss-120b | default | $0.0014/request | - | 1637.3 t/s | 0.91 s | — | |
L1 100% | gpt-oss-120b-medium | default | $0.055/M | $0.110/M | 255.8 t/s | 1.45 s | — | |
L1 100% | gpt-oss-120b | default | $4.38/M Audio in$0.219/M | $13.14/M | 1319.0 t/s | 0.61 s | — | |
L1 99% | gpt-oss-120b | 无限制 | $0.073/request | - | 1201.8 t/s | 0.78 s | ||
L1 99% | gpt-oss-20b | 91vip | $0.438/M Cache read$0.0013/MCache write$0.026/MCache write 1h$0.042/M | $0.048/M | 216.3 t/s | 1.31 s | ||
L1 100% | FAST/gpt-oss-120b | 临时渠道 | $0.041/M | $0.014/M | 819.1 t/s | 0.87 s | ||
L1 100% | gpt-oss-120b | 翻译 | $0.068/M | $0.288/M | 126.7 t/s | 0.79 s | — | |
L1 100% | openai/gpt-oss-20b | 0倍倍率分组 | $0.0004/M Cache read$0.0002/M | $0.0022/M | — | — | — | |
L1 100% | openai/gpt-oss-120b | 0倍倍率分组 | $0.0021/M Cache read$0.0002/M | $0.0082/M | — | — | — | |
L1 97% | openai/gpt-oss-20b | default | $0.010/request | - | 234.4 t/s | 1.48 s | — | |
L1 97% | openai/gpt-oss-120b | default | $0.010/request | - | — | — | — | |
L1 97% | openai/gpt-oss-20b:free | default | $0.010/request | - | — | — | — | |
L1 97% | openai/gpt-oss-120b:free | default | $0.010/request | - | — | — | — | |
L1 77% | openai/gpt-oss-120b | default | $359.64/M Cache read$359.64/M | $1798.20/M | 124.7 t/s | 2.30 s | ||
L1 77% | openai/gpt-oss-20b | default | $289.71/M Cache read$289.71/M | $1398.60/M | — | — | — | |
L1 100% | gpt-oss-120b | default | $0.018/request | - | — | — | — | |
L1 100% | gpt-oss-20b | default | $0.014/M | $0.055/M | — | — | — | |
L1 100% | gpt-oss-120b | default | $0.075/M | $0.301/M | — | — | — | |
Dext API Free | L1 100% | gpt-oss-20b | 公益 | Free | Free | — | — | — |
L1 100% | gpt-oss-120b | 公益 | Free | Free | — | — | — |
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
