Gemini 4 Carbon vs Inkling Small

Side-by-side pricing per provider, context window, benchmark scores and speed, all on one OpenAI-compatible API.

Estimate monthly cost for these models
Metric
Gemini 4 CarbonGooglegoogle/gemini-4-carbon
Inkling SmallThinking Machinesthinkingmachines/inkling-small
Creator
Google
Thinking Machines
Released
Nov 10, 2026
Jul 30, 2026
Context window
1.05M (best)
524K
Input / 1MLowest provider price
$2.00
$0.45 (best)
Output / 1MLowest provider price
$10.00
$1.20 (best)
Providers
1
1
IntelligenceArtificial Analysis index
60.0 (best)
12.9
LatencyMedian time to first token
50s
396ms (best)
ThroughputMedian tokens per second
<1 t/s (best)
<1 t/s
Accepts
Text, Image, Audio, Video, Files
Text, Image, Audio
Produces
Text
Text
Tool calling
Yes
Yes
Structured output
No
Yes
Reasoning
No
Yes

Gemini 4 Carbon vs Inkling Small: summary

Gemini 4 Carbon and Inkling Small are both available through FastRouter's OpenAI-compatible API, so switching between them is a change of model id, not a new integration.

Gemini 4 Carbon, from Google, has a 1,048,576-token context window, costs $2.00/1M input and $10.00/1M output tokens and scores 60.0 on the Artificial Analysis Intelligence Index.

Inkling Small, from Thinking Machines, has a 524,288-token context window, costs $0.45/1M input and $1.20/1M output tokens and scores 12.9 on the Artificial Analysis Intelligence Index.

Inkling Small is the cheapest on input, 4.4× cheaper than the next model, Gemini 4 Carbon has the largest context window, Gemini 4 Carbon scores highest for intelligence and Gemini 4 Carbon has the highest throughput.

Switch with one line

client = OpenAI(base_url="https://api.fastrouter.ai/api/v1", api_key="<FASTROUTER_API_KEY>") client.chat.completions.create(model="google/gemini-4-carbon", messages=[...]) # or client.chat.completions.create(model="thinkingmachines/inkling-small", messages=[...])
Full API docs

Frequently asked questions

More comparisons

Benchmark scores sourced from ArtificialAnalysis