Phaseo

Grok 4.6 vs Inkling 2 Small

Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.

Try Grok 4.6 in Chat
Grok 4.6
Inkling 2 Small

At a glance

Generated from the rows below

Choose Grok 4.6 for

  • The most routes on Phaseo: 4

Choose Inkling 2 Small for

  • The lowest cost per typical request ($0.0011)
  • The largest context window: 1,000,000 tokens

Overview

Lab
SpaceXAI
Thinking Machines Lab
Context window
500Ktokens
1Mtokens (best)
Max output
500Ktokensfrom provider listings
Not published
Takes
Text, Image
Text, Image
Returns
Text
Text
Routes on Phaseo
4 providers
 (best)
1 provider
Released
12 Aug 2026
5 Nov 2026

Pricing

Prices on the route and tier chosen under each model

SpaceXAI · StandardThinking Machines · Standard
Input
from $2.00/ 1M tokensInput < 200K$2.00Input ≥ 200K$4.00
$0.30/ 1M tokens
Output
from $6.00/ 1M tokensInput < 200K$6.00Input ≥ 200K$12.00
$1.00/ 1M tokens
Cache read
from $0.50/ 1M tokensInput < 200K$0.50Input ≥ 200K$1.00
$0.03/ 1M tokens
Typical request2K tokens in, 500 out
$0.007
$0.0011 (best)

What will it cost?

Estimate a month of requests on the route and tier chosen for each model

ModelPer requestPer month
Grok 4.6SpaceXAI · Standard$0.007$210.00
Inkling 2 SmallThinking Machines · Standard$0.0011$33.00

Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.

Performance

Live gateway traffic

Latency p50
No traffic in the last 5 days
No traffic in the last 5 days
Throughput p50
No traffic in the last 5 days
No traffic in the last 5 days
Requests, last 24 hours
None in the last 24 hours
None in the last 24 hours

Activity

Tokens sent through Phaseo each day over the last 30 days

None of these models has had traffic through Phaseo in the last 30 days.

Features

Features from the parameters Phaseo routes support

Tool calling
Yes
Not listed
Structured outputs
Yes
Not listed
Reasoning effort
Yes
Not listed
Web search
Yes
Not listed
Prompt cachingon the chosen route
Yes
Yes
Quantisationon the chosen route
Not stated
Not stated

Benchmarks

Only results that two or more of the selected models report get a row

Compare at effort

Artificial Analysis Intelligence Index Independent

Higher is better · at Extra high effort · 1 of 2 models tested

Grok 4.631
Inkling 2 Small30.6

Where they rank

The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.

Artificial Analysis Intelligence Index54 models ranked

  1. #1Claude Opus 5.559.1
  2. #2GPT-6 Astra56.9
  3. #3GPT-6.1 Sol54.6
  4. #4Claude Sonnet 5.554.5
  5. #5GPT-6.1 Terra51.3
  6. #20Grok 4.631.0
  7. #22Inkling 2 Small30.6

Artificial Analysis Coding Index171 models ranked

  1. #1Claude Fable 5.181.6
  2. #2GPT 5.6 Sol78.3
  3. #3Claude Opus 578.0
  4. #4GPT-6 Astra77.1
  5. #5Grok 4.676.8

Artificial Analysis Agentic Index112 models ranked

  1. #1Claude Fable 5.157.9
  2. #2Claude Opus 556.5
  3. #3Qwen 3.8 Max 090256.0
  4. #4Muse Spark 1.355.5
  5. #5Qwen 3.8 Flash Next53.6
  6. #7Grok 4.653.0

Epoch Capabilities Index164 models ranked

  1. #1GPT-6 Astra169.1
  2. #2GPT-6.1 Sol168.9
  3. #3Claude Opus 5.5168.4
  4. #4GPT-6.1 Terra167.8
  5. #5Claude Fable 5.1166.9
  6. #23Grok 4.6157.9
Cost
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$3,391
$791.81 (best)

Lab-reported results come from each lab’s own launch materials and may use different settings, so none is marked best. Independent results come from third-party evaluators.

Providers

Where each model runs on Phaseo, with standard-tier prices per 1M tokens. Providers that serve more of these models come first.

SpaceXAI
$2.00 in · $6.00 out$5.00 per 1K requests Native web search requests500K context · Standard, Priority
—
Thinking Machines
—
$0.30 in · $1.00 out262K context
GMICloud
$2.00 in · $6.00 out500K context
—
Inference.net
$2.00 in · $6.00 out500K context
—
Venice
$2.27 in · $6.80 outfrom $10.00 per 1K requests Web search500K context
—
Also listed, not routed
8 providers
—

To price the whole page on one of these providers, pick it under the model’s name at the top.

Details

Knowledge cutoff
Not published
Not published
Status
Available
Available
Licence
Proprietary
Proprietary
Subscription plans
15 plansCursor Enterprise, Cursor Pro, Cursor Pro+…
None mapped
API docs
Open docs
Not published

Grok 4.6 vs Inkling 2 Small: side-by-side summary

Grok 4.6 and Inkling 2 Small are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.

Grok 4.6 is from SpaceXAI. It has a 500,000-token context window. On its cheapest route it costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

Inkling 2 Small is from Thinking Machines Lab. It has a 1,000,000-token context window. On its cheapest route it costs $0.30 per 1M input tokens and $1.00 per 1M output tokens.

Grok 4.6 model details, providers and pricingInkling 2 Small model details, providers and pricing

Grok 4.6 vs Inkling 2 Small at a glance

Grok 4.6 and Inkling 2 Small compared on price, context window and benchmark score
AttributeGrok 4.6Inkling 2 Small
LabSpaceXAIThinking Machines Lab
Input price per 1M tokens$2.00$0.30
Output price per 1M tokens$6.00$1.00
Context window500,000 tokens1,000,000 tokens
Max output500,000 tokensNot listed
Artificial Analysis Intelligence Index31.0 (#20)30.6 (#22)

Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.

Frequently asked questions

Which is cheaper, Grok 4.6 or Inkling 2 Small?

Inkling 2 Small is cheaper for both input and output tokens. Grok 4.6 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens; Inkling 2 Small costs $0.30 and $1.00, each on its cheapest standard route on Phaseo.

Which has the longer context window, Grok 4.6 or Inkling 2 Small?

Inkling 2 Small has the longer context window at 1,000,000 tokens, compared with 500,000 tokens for Grok 4.6.

Which scores higher on the Artificial Analysis Intelligence Index, Grok 4.6 or Inkling 2 Small?

Grok 4.6 scores higher on the Artificial Analysis Intelligence Index. Grok 4.6 scores 31.0, ranked #20 of 54. Inkling 2 Small scores 30.6, ranked #22 of 54.

Can I use Grok 4.6 and Inkling 2 Small through one API?

Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.

Help keep public data accurate

See something missing, incorrect, or out of date? Tell us about this page.