How much does O3 cost per million tokens?
O3 costs $2.00/1M input tokens and $8.00/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
O3 costs $2.00/1M input tokens and $8.00/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 200K tokens context window. o10 lists O3 on OpenAI at routing band C3.
Last updated: 2026-06-27. Full catalog
O3 pricing — input/output per 1M tokens
AnswersSelf-contained
Where can you run O3?
O3 is configured on OpenAI. 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 O3's context window?
O3 supports a 200K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
01Deep dive
Token pricing
Gateway snapshot pricing for O3.
| Unit | Price |
|---|---|
| Input | $2/1M tokens |
| Output | $8/1M tokens |
02Deep dive
Fulfillment hosts
Upstream venues configured for O3.
| Host | Upstream model ID |
|---|---|
| openai | openai/o3 |
03Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: o3. Band: C3. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
SourceMethodology
Gateway catalog snapshot 2026-06-27. Fulfillment catalog synced from o10 control plane. Verify list prices against openrouter and host providers.
FAQFrequently asked questions
Common questions
How much does O3 cost?
O3 costs $2.00/1M input tokens and $8.00/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is O3's context window?
O3 supports 200K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve O3?
O3 (o3) is configured on: OpenAI. Upstream model IDs are listed in the fulfillment routes section.
Is O3 routable through o10?
Yes. O3 is routable at band C3. Send model: "o3" or use an o10 smart routing alias.
How do I call O3 via o10?
Use o10 slug "o3" or gateway ID "openai/o3" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes O3 only when per-use-case evals clear at your quality floor. Band C3 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.