GPT-4o costs $2.50/1M input tokens and $10.00/1M output tokens as of 2026-06-27. OpenAI publishes this model with a 128K tokens context window. o10 lists GPT-4o on OpenRouter at routing band C2. API slug openai-gpt-4o. 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-4o is a chat model from openai (slug: openai-gpt-4o). Pick GPT-4o when you need OpenAI's general chat/vision family at this generation. It is the named GPT SKU, not a reasoning-only o-series model. Published input pricing starts at $2.50/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Pick GPT-4o when you need OpenAI's general chat/vision family at this generation. It is the named GPT SKU, not a reasoning-only o-series model. GPT-4o has cheaper mini/nano siblings for high-volume work. Pin the full SKU only when evals fail on the smaller tier.
GPT-4o has cheaper mini/nano siblings for high-volume work. Pin the full SKU only when evals fail on the smaller tier.
GPT-4o costs $2.50/1M input tokens and $10.00/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
GPT-4o is configured on OpenRouter. Known host IDs: openrouter: openrouter/openai/gpt-4o. This model is routable through o10 eval-gated routing.
GPT-4o supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
GPT-4o is classified at o10 routing band C2. 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-4o is attributed to source provider openai in the o10 catalog. Fulfillment hosts (OpenRouter) supply API access; list pricing may differ by venue.
GPT-4o in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `openai-gpt-4o` |
| Type | text |
| Band | C2 |
| Routable | Yes |
| Source provider | openai |
| Primary host | OpenRouter |
| Gateway ID | `openai/gpt-4o` |
| Context window | 128,000 tokens |
| Released | 2024-05-13 |
Gateway snapshot pricing for GPT-4o.
| Unit | Price |
|---|---|
| Input | $2.5/1M tokens |
| Output | $10/1M tokens |
Upstream venues configured for GPT-4o.
| Host | Upstream model ID |
|---|---|
| openrouter | openrouter/openai/gpt-4o |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| azure | $2.5 | 353ms | 9999.2% |
| openai | $2.5 | 567ms | 9998.5% |
Eval-gated model selection for this slug.
o10 slug: openai-gpt-4o. Band: C2. 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-4o costs $2.50/1M input tokens and $10.00/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
GPT-4o supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
GPT-4o (openai-gpt-4o) is configured on: OpenRouter. Upstream model IDs are listed in the fulfillment routes section.
Yes. GPT-4o is routable at band C2. Send model: "openai-gpt-4o" or use an o10 smart routing alias.
Use o10 slug "openai-gpt-4o" or gateway ID "openai/gpt-4o" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes GPT-4o only when per-use-case evals clear at your quality floor. Band C2 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.
The o10 slug is "openai-gpt-4o"; the unified gateway ID is "openai/gpt-4o". Host IDs: openrouter: openrouter/openai/gpt-4o. Pricing snapshot date: 2026-06-27.
GPT-4o is hosted as openrouter: openrouter/openai/gpt-4o. o10 maps those upstream IDs to slug "openai-gpt-4o".