Grok 4.20 Reasoning costs $1.25/1M input tokens and $2.50/1M output tokens as of 2026-06-27. xAI publishes this model with a 2M tokens context window. o10 lists Grok 4.20 Reasoning on xAI at routing band C4. API slug grok-4.20-reasoning. 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.
Grok 4.20 Reasoning is a chat model from xai (slug: grok-4.20-reasoning). Pick Grok 4.20 Reasoning when the job needs xAI Grok (or Cursor's Grok pool) and evals justify the band. Published input pricing starts at $1.25/1M tokens. Context window: 2M tokens.
Catalog snapshot 2026-06-27.
Pick Grok 4.20 Reasoning when the job needs xAI Grok (or Cursor's Grok pool) and evals justify the band. Grok 4.20 Reasoning is a Grok generation, not a Claude or GPT SKU. Compare against the previous Grok and against Gemini Flash on cost.
Grok 4.20 Reasoning is a Grok generation, not a Claude or GPT SKU. Compare against the previous Grok and against Gemini Flash on cost.
Grok 4.20 Reasoning costs $1.25/1M input tokens and $2.50/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Grok 4.20 Reasoning is configured on xAI. Known host IDs: xai: xai/grok-4.20-reasoning. This model is routable through o10 eval-gated routing.
Grok 4.20 Reasoning supports a 2M tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Grok 4.20 Reasoning 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.
Grok 4.20 Reasoning is attributed to source provider xai in the o10 catalog. Fulfillment hosts (xAI) supply API access; list pricing may differ by venue.
Grok 4.20 Reasoning in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `grok-4.20-reasoning` |
| Type | text |
| Band | C4 |
| Routable | Yes |
| Source provider | xai |
| Primary host | xAI |
| Gateway ID | `xai/grok-4.20-reasoning` |
| Context window | 2,000,000 tokens |
| Released | 2026-03-09 |
Gateway snapshot pricing for Grok 4.20 Reasoning.
| Unit | Price |
|---|---|
| Input | $1.25/1M tokens |
| Output | $2.5/1M tokens |
Upstream venues configured for Grok 4.20 Reasoning.
| Host | Upstream model ID |
|---|---|
| xai | xai/grok-4.20-reasoning |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| vertex | $2 | 888ms | 10000.0% |
| xai | $1.25 | 380ms | 10000.0% |
Eval-gated model selection for this slug.
o10 slug: grok-4.20-reasoning. Band: C4. 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.
Grok 4.20 Reasoning costs $1.25/1M input tokens and $2.50/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Grok 4.20 Reasoning supports 2M tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Grok 4.20 Reasoning (grok-4.20-reasoning) is configured on: xAI. Upstream model IDs are listed in the fulfillment routes section.
Yes. Grok 4.20 Reasoning is routable at band C4. Send model: "grok-4.20-reasoning" or use an o10 smart routing alias.
Use o10 slug "grok-4.20-reasoning" or gateway ID "xai/grok-4.20-reasoning" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Grok 4.20 Reasoning 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.