GPT-5 nano costs $0.050/1M input tokens and $0.400/1M output tokens as of 2026-06-27. OpenAI publishes this model with a 400K tokens context window. o10 lists GPT-5 nano on OpenRouter at routing band C0. API slug openai-gpt-5-nano. Verify list prices against the venue you call.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
GPT-5 nano is a chat model from openai (slug: openai-gpt-5-nano). Pick GPT-5 nano for the cheapest OpenAI GPT-5 class calls. Use it for classification, extract, and short replies. Published input pricing starts at $0.050/1M tokens. Context window: 400K tokens.
Catalog snapshot 2026-06-27.
Pick GPT-5 nano for the cheapest OpenAI GPT-5 class calls. Use it for classification, extract, and short replies. GPT-5 nano is below GPT-5 mini. Escalate to mini or full GPT-5 when the task needs longer reasoning.
GPT-5 nano is below GPT-5 mini. Escalate to mini or full GPT-5 when the task needs longer reasoning.
GPT-5 nano costs $0.050/1M input tokens and $0.400/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
GPT-5 nano is configured on OpenRouter. Known host IDs: openrouter: openrouter/openai/gpt-5-nano. This model is routable through o10 eval-gated routing.
GPT-5 nano supports a 400K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
GPT-5 nano is classified at o10 routing band C0. 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.
GPT-5 nano is attributed to source provider openai in the o10 catalog. Fulfillment hosts (OpenRouter) supply API access; list pricing may differ by venue.
GPT-5 nano in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `openai-gpt-5-nano` |
| Type | text |
| Band | C0 |
| Routable | Yes |
| Source provider | openai |
| Primary host | OpenRouter |
| Gateway ID | `openai/gpt-5-nano` |
| Context window | 400,000 tokens |
| Released | 2025-08-07 |
Gateway snapshot pricing for GPT-5 nano.
| Unit | Price |
|---|---|
| Input | $0.05/1M tokens |
| Output | $0.4/1M tokens |
Upstream venues configured for GPT-5 nano.
| Host | Upstream model ID |
|---|---|
| openrouter | openrouter/openai/gpt-5-nano |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| azure | $0.05 | 4590ms | 9998.5% |
| openai | $0.05 | 5464ms | 9997.4% |
Eval-gated model selection for this slug.
o10 slug: openai-gpt-5-nano. Band: C0. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
GPT-5 nano costs $0.050/1M input tokens and $0.400/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
GPT-5 nano supports 400K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
GPT-5 nano (openai-gpt-5-nano) is configured on: OpenRouter. Upstream model IDs are listed in the fulfillment routes section.
Yes. GPT-5 nano is routable at band C0. Send model: "openai-gpt-5-nano" or use an o10 smart routing alias.
Use o10 slug "openai-gpt-5-nano" or gateway ID "openai/gpt-5-nano" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes GPT-5 nano only when per-use-case evals clear at your quality floor. Band C0 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.
The o10 slug is "openai-gpt-5-nano"; the unified gateway ID is "openai/gpt-5-nano". Host IDs: openrouter: openrouter/openai/gpt-5-nano. Pricing snapshot date: 2026-06-27.
GPT-5 nano is hosted as openrouter: openrouter/openai/gpt-5-nano. o10 maps those upstream IDs to slug "openai-gpt-5-nano".