Gemini 4 Carbon
prime/google/gemini-4-carbon · family gemini · in: audio, image, text, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning audio image text video.
$4.00
Blended $/1M (3:1)
$2
Input $/1M
$10
Output $/1M
$12.00
1M in + 1M out
—
Cache read $/1M
#6938 of 8,720
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 943,718 tokens
- Capabilities
- tools reasoning audio image text video
Same model, other providers
“Gemini 4 Carbon” is offered by 15 providers — cheapest-effective first. This one (Prime Inference) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Prime Inference (this) | $2 | $10 | $4.00 | 1M |
| OpenCode | $2 | $10 | $4.00 | 1M |
| Vertex | $2 | $10 | $4.00 | 1M |
| Cloudflare AI Gateway | $2 | $10 | $4.00 | 1M |
| CrossModel | $2 | $10 | $4.00 | 1M |
| Vercel AI Gateway | $2 | $10 | $4.00 | 1M |
| $2 | $10 | $4.00 | 1M | |
| NanoGPT | $2 | $10 | $4.00 | 1M |
| OpenRouter | $2 | $10 | $4.00 | 1M |
| GitHub Copilot | $2 | $10 | $4.00 | 1M |
| Merge Gateway | $2 | $10 | $4.00 | 1M |
| Cortecs | $2.23 | $11.15 | $4.46 | 1M |
| Venice AI | $2.5 | $12.5 | $5.00 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"google/gemini-4-carbon","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):