Grok 4.3
abacus/grok-4.3 · family grok · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$1.56
Blended $/1M (3:1)
$1.25
Input $/1M
$2.5
Output $/1M
$3.75
1M in + 1M out
$0.2 −84%
Cache read $/1M
#5200 of 8,511
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Grok 4.3” is offered by 29 providers — cheapest-effective first. This one (Abacus) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Abacus (this) | $1.25 | $2.5 | $1.56 | 1M |
| Vertex | $1.25 | $2.5 | $1.56 | 200k |
| Vercel AI Gateway | $1.25 | $2.5 | $1.56 | 1M |
| Requesty | $1.25 | $2.5 | $1.56 | 1M |
| Impossibl | $1.25 | $2.5 | $1.56 | 1M |
| Tempr Gateway | $1.25 | $2.5 | $1.56 | 1M |
| Auriko | $1.25 | $2.5 | $1.56 | 1M |
| Opper | $1.25 | $2.5 | $1.56 | 1M |
| 302.AI | $1.25 | $2.5 | $1.56 | 1M |
| AIHubMix | $1.25 | $2.5 | $1.56 | 1M |
| Amazon Bedrock | $1.25 | $2.5 | $1.56 | 1M |
| Eden AI | $1.25 | $2.5 | $1.56 | 1M |
| FrogBot | $1.25 | $2.5 | $1.56 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"grok-4.3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):