gpt-oss-120b
OpenAI · Open weights · Released Aug 5, 2025 · openai/gpt-oss-120b
Best $0.03 in / $0.15 out via AkashML · fp4
131K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 25 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 6 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.03 | $0.187 | $0.03 | 131K | fp4 | ✕ | ✕ | 4/5 | 100.0% | |
| $0.03 | $0.17 | $0.03 | 131K | fp4 | 0.6s° | 146° tok/s | 3/5 | 99.9% | |
| DEDekaLLM | $0.03 | $0.18 | $0.03 | 131K | bf16 | 1.1s° | 67° tok/s | — | 69.9% |
| $0.03 | $0.15 | $0.015 | 131K | fp4 | 1.6s° | 73° tok/s | — | 100.0% | |
| $0.03 | $0.15 | $0.03 | 128K | int4 | 17.4s° | 59° tok/s | — | 99.8% | |
| $0.037 | $0.17 | $0.018 | 131K | bf16 | 0.58s° | 38° tok/s | 4/5 | 76.3% | |
| $0.05 | $0.25 | $0.05 | 131K | bf16 | 0.42s° | 268° tok/s | — | 100.0% | |
| $0.06 | $0.42 | $0.012 | 128K | — | 0.96s° | 53° tok/s | 4/5 | 100.0% | |
| $0.085 | $0.375 | $0.085 | 131K | fp8 | 1.2s° | 132° tok/s | — | 99.5% | |
| $0.09 | $0.36 | — | 131K | — | 46.1s° | 326° tok/s | — | 99.9% | |
| $0.10 | $0.50 | $0.10 | 128K | fp4 | 0.21s° | 236° tok/s | — | 99.8% | |
| $0.10 | $0.50 | $0.10 | 128K | fp4 | — | — | — | 99.6% | |
| $0.10 | $0.75 | $0.055 | 131K | fp4 | 0.6s° | 297° tok/s | — | 100.0% | |
| $0.135 | $0.54 | $0.068 | — | — | ✕ | ✕ | — | — | |
| $0.14 | $0.95 | — | 131K | — | 1s° | 1143° tok/s | — | 99.5% | |
| $0.15 | $0.60 | — | 131K | — | 0.7s° | — | — | 100.0% | |
| $0.15 | $0.60 | — | 131K | — | — | — | — | 99.9% | |
| $0.15 | $0.60 | $0.015 | 131K | — | — | — | — | 76.3% | |
| $0.15 | $0.60 | $0.075 | 131K | — | 0.7s | 484 tok/s | — | 99.0% | |
| $0.15 | $0.60 | $0.10 | 131K | fp4 | 0.63s° | 319° tok/s | — | 99.6% | |
| $0.15 | $0.75 | — | 131K | fp4 | — | — | — | 100.0% | |
| $0.15 | $0.60 | $0.075 | 131K | fp8 | 2.3s° | 100° tok/s | 3/5 | 95.0% | |
| $0.15 | $0.60 | — | 131K | — | 0.37s° | 155° tok/s | — | 97.7% | |
| $0.35 | $0.75 | $0.35 | 131K | fp16 | 0.47s | 1702 tok/s | — | 100.0% | |
| $0.35 | $0.75 | $0.315 | 131K | fp4 | 10.4s° | 156° tok/s | — | 96.1% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured against the provider API directly; ° = routed via OpenRouter (adds a hop) · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 6 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↑ 200% SINCE NOV 8, 2026
$0.01 · NOV 8, 2026$0.03 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.03 / $0.187
per MTok in / out
BATCH
$0.03 / $0.136
async batch
CACHE READ $0.03
Recent changesRSS ↗
Nov 22, 2026endpoint added · fireworks24 → 25
Nov 21, 2026endpoint removed · sail-research25 → 24
Nov 18, 2026price increased · output0.086 → 0.15
Nov 17, 2026endpoint removed · io-net27 → 25
Nov 13, 2026price increased · output0.075 → 0.099
Nov 12, 2026endpoint added · io-net26 → 27
Nov 11, 2026endpoint removed · phala27 → 26
Nov 10, 2026price increased · output0.075 → 0.077
About
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...
Specifications
Context window131,072
Max output117,964
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedAug 5, 2025
Knowledge cutoff2024-06-30
TokenizerGPT
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/openai/gpt-oss-120b)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks6 minutes ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.