Grok 4.3 pricing
Grok 4.3, Mid-tier from xAI, costs $1.25 per 1M input tokens and $2.50 per 1M output tokens.
Input$1.25per 1M tokens
Output$2.50per 1M tokens
Context window1Mtokens
TierMidxAI
Price your own workload against Grok 4.3 in the calculator →
Specs and pricing
| Provider | xAI |
| Tier | Mid |
| Context window | 1M tokens |
| Max output | — |
| Input price | $1.25 / 1M tokens |
| Output price | $2.50 / 1M tokens |
| Cache read | $0.20 / 1M tokens |
| Modalities | text, image |
Note. Short-context rate, for prompts under 200K tokens. At 200K and above: $2.50 input / $5 output, cache read $0.40 per 1M. Eligible for a 20% Batch API discount.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $1.25 | $0.63 | $1.88 |
| 10,000,000 in / 2,500,000 out | $12.50 | $6.25 | $18.75 |
| 100,000,000 in / 25,000,000 out | $125.00 | $62.50 | $187.50 |
Cheaper alternatives
Same tier (Mid), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| GPT-OSS 120B | OpenRouter | $0.037 | $0.17 | 95.8% cheaper blended |
| GPT-OSS 120B | Novita AI | $0.05 | $0.25 | 94% cheaper blended |
| Llama-3.3-70B-Instruct-Turbo | DeepInfra | $0.10 | $0.32 | 90.4% cheaper blended |
| Nemotron 3 Super | OpenRouter | $0.085 | $0.40 | 90.1% cheaper blended |
| DeepSeek V4 Flash 0731 | Baseten | $0.13 | $0.26 | 89.6% cheaper blended |