What is Gpt Oss 120b?
Gpt Oss 120b is a language model in the o10 fulfillment catalog (slug: gpt-oss-120b). Published input pricing starts at $0.350/1M tokens. Context window: 131K tokens.
Catalog snapshot 2026-06-27.
Gpt Oss 120b costs $0.350/1M input tokens and $0.750/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 131K tokens context window. o10 lists Gpt Oss 120b on OpenAI and SambaNova at routing band C4.
Last updated: 2026-06-27. Full catalog
Gpt Oss 120b — specs, hosts, and routing
AnswersSelf-contained
How much does Gpt Oss 120b cost per million tokens?
Gpt Oss 120b costs $0.350/1M input tokens and $0.750/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Where can you run Gpt Oss 120b?
Gpt Oss 120b is configured on OpenAI and SambaNova. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
What is Gpt Oss 120b's context window?
Gpt Oss 120b supports a 131K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Gpt Oss 120b?
Gpt Oss 120b is classified at o10 routing band C4. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
Who makes Gpt Oss 120b?
Gpt Oss 120b is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (OpenAI and SambaNova) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Gpt Oss 120b in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `gpt-oss-120b` |
| Type | text |
| Band | C4 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | OpenAI |
| Gateway ID | `openai/gpt-oss-120b` |
| Context window | 131,072 tokens |
| Released | 2025-08-05 |
02Deep dive
Token pricing
Gateway snapshot pricing for Gpt Oss 120b.
| Unit | Price |
|---|---|
| Input | $0.35/1M tokens |
| Output | $0.75/1M tokens |
03Deep dive
Fulfillment hosts
Upstream venues configured for Gpt Oss 120b.
| Host | Upstream model ID |
|---|---|
| openai | openai/gpt-oss-120b |
| openai | sambanova/gpt-oss-120b |
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| baseten | $0.1 | 141.5ms | 10000.0% |
| bedrock | $0.15 | 365.5ms | 9871.2% |
| cerebras | $0.35 | 218ms | 9981.4% |
| fireworks | $0.15 | 122ms | 9905.2% |
| groq | $0.15 | 297ms | 10000.0% |
| nebius | $0.15 | 474.5ms | 10000.0% |
| parasail | $0.1 | 257ms | 10000.0% |
| togetherai | $0.15 | 567ms | 9785.2% |
05Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: gpt-oss-120b. Band: C4. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/economy) and [/kyi](/kyi) for governance.
SourceMethodology
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
FAQFrequently asked questions
Common questions
How much does Gpt Oss 120b cost?
Gpt Oss 120b costs $0.350/1M input tokens and $0.750/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Gpt Oss 120b's context window?
Gpt Oss 120b supports 131K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Gpt Oss 120b?
Gpt Oss 120b (gpt-oss-120b) is configured on: OpenAI and SambaNova. Upstream model IDs are listed in the fulfillment routes section.
Is Gpt Oss 120b routable through o10?
Yes. Gpt Oss 120b is routable at band C4. Send model: "gpt-oss-120b" or use an o10 smart routing alias.
How do I call Gpt Oss 120b via o10?
Use o10 slug "gpt-oss-120b" or gateway ID "openai/gpt-oss-120b" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Gpt Oss 120b only when per-use-case evals clear at your quality floor. Band C4 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.