xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning
Specification
most-agreed values
Context
2M
Max output
30K
Released
2025-11-19
Knowledge cutoff
2025-06
Retires
2027-05-19
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.20
Output
$0.50
Cache read
$0.05
Available from 14 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| jiekou | $0.19 | $0.475 | — | — | 2M | 30K | — |
| 302ai | $0.20 | $0.50 | — | — | 2M | 30K | — |
| azure | $0.20 | $0.50 | $0.05 | — | 128K | 8K | — |
| azure_ai | $0.20 | $0.50 | — | — | 128K | 128K | 2027-05-19 |
| azure-cognitive-services | $0.20 | $0.50 | $0.05 | — | 128K | 8K | — |
| frogbot | $0.20 | $0.50 | $0.05 | — | 2M | 128K | — |
| google-vertex | $0.20 | $0.50 | $0.05 | — | 128K | 30K | — |
| helicone | $0.20 | $0.50 | $0.05 | — | 2M | 2M | — |
| llmgateway | $0.20 | $0.50 | $0.05 | — | 2M | 30K | — |
| llmgateway-providers | $0.20 | $0.50 | — | — | 128K | 128K | — |
| llmgateway-providers · azure-ai-foundry | $0.20 | $0.50 | — | — | 128K | 30K | — |
| vertex_ai | $0.20 | $0.50 | $0.05 | — | 128K | 128K | — |
| poe | — | — | — | — | 2M | 30K | — |
| qiniu-ai · x-ai | — | — | — | — | 20M | 2M | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | jiekou | Input | $0.18 |
| 2026-10-22 | jiekou | Input | $0.19 |
| 2026-09-02 | jiekou | Output | $0.45 |
| 2026-10-22 | jiekou | Output | $0.475 |
More from xAI
most-hosted first