Gpt Oss 20b costs $0.050/1M input tokens and $0.200/1M output tokens as of 2026-06-27. Openai publishes this model with a 131K tokens context window. o10 lists Gpt Oss 20b on OpenRouter and NVIDIA NIM at routing band C1.
Last updated: 2026-06-27. Full catalog
Gpt Oss 20b costs $0.050/1M input tokens and $0.200/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Gpt Oss 20b is configured on OpenRouter and NVIDIA NIM. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
Gpt Oss 20b supports a 131K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Gateway snapshot pricing for Gpt Oss 20b.
| Unit | Price |
|---|---|
| Input | $0.05/1M tokens |
| Output | $0.2/1M tokens |
Upstream venues configured for Gpt Oss 20b.
| Host | Upstream model ID |
|---|---|
| openrouter | openrouter/openai/gpt-oss-20b |
| openrouter | nvidia_nim/openai/gpt-oss-20b |
Eval-gated model selection for this slug.
o10 slug: openai-gpt-oss-20b. Band: C1. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
Gateway catalog snapshot 2026-06-27. Fulfillment catalog synced from o10 control plane. Verify list prices against openai and host providers.
Gpt Oss 20b costs $0.050/1M input tokens and $0.200/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Gpt Oss 20b supports 131K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Gpt Oss 20b (openai-gpt-oss-20b) is configured on: OpenRouter and NVIDIA NIM. Upstream model IDs are listed in the fulfillment routes section.
Yes. Gpt Oss 20b is routable at band C1. Send model: "openai-gpt-oss-20b" or use an o10 smart routing alias.
Use o10 slug "openai-gpt-oss-20b" or gateway ID "openai/gpt-oss-20b" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Gpt Oss 20b only when per-use-case evals clear at your quality floor. Band C1 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.