Inkling-Small vs Phi-3.5-vision-instruct

    Comparison

    As of August 30, 2026, Phi-3.5-vision-instruct is 86% cheaper per million tokens than Inkling-Small. Inkling-Small is $0.30 / $1.20 per million input/output tokens versus Phi-3.5-vision-instruct at $0.07 / $0.14. Sources: https://thinkingmachines.ai and https://azure.microsoft.com/pricing/details/phi-3/

    Sources: Thinking Machines Lab pricing (https://thinkingmachines.ai); Microsoft pricing (https://azure.microsoft.com/pricing/details/phi-3/)

    Inkling-Small

    Thinking Machines

    $1.50blended / 1M

    Input

    $0.30

    Output

    $1.20

    256K ctx|Open Source
    86%
    cheaper
    Better value

    Phi-3.5-vision-instruct

    Microsoft

    $0.21blended / 1M

    Input

    $0.07

    Output

    $0.14

    128K ctx|Open Source
    Save $1.29 per million tokens by choosing Phi-3.5-vision-instruct over Inkling-Small.

    Inkling-Small vs Phi-3.5-vision-instruct comparison

    Token pricing, specs, and benchmarks side by side

    Metric
    Inkling-Small
    Phi-3.5-vision-instruct
    Provider
    Provider
    Thinking Machines
    Microsoft
    License
    Open Source
    Open Source
    Release Date
    2026-07-30
    2024-08-23
    Pricing (per 1M tokens)
    Input Price+329%
    $0.30
    $0.07
    Output Price+757%
    $1.20
    $0.14
    Blended (1M + 1M)
    $1.50
    $0.21
    Model Details
    Context Window
    256K
    128K
    Max Output Tokens
    256K
    N/A
    Knowledge Cutoff
    N/A
    N/A
    Throughput
    N/A
    N/A
    Benchmarks
    31.6%
    89.5%
    88.5%
    48.7%
    77.4%
    19.5%
    82.2%
    40.1%
    54.4%
    79.6%
    74%
    77.4%
    90%
    43%
    30.6%
    78.1%
    95.5%
    84%
    81.8%
    69.6%
    8.3%
    68.8%
    31.8%
    42.3%
    36.3%
    43.9%
    37.9%
    84.1%
    77%
    81.9%
    85.6%
    86.1%
    32.7%
    91.3%
    91.3%
    33.6%
    15.5%
    75.5%
    72%

    Verdict

    Inkling-Small vs Phi-3.5-vision-instruct: the bottom line

    Both models are closely matched on benchmarks. Phi-3.5-vision-instruct has the pricing advantage, making it the better value unless Inkling-Small's specific capabilities are critical to your workflow.

    Inkling-Small vs Phi-3.5-vision-instruct FAQ

    Which is cheaper, Inkling-Small or Phi-3.5-vision-instruct?

    As of August 30, 2026, Phi-3.5-vision-instruct is 86% cheaper on blended LLM API pricing. Phi-3.5-vision-instruct costs $0.07 per million input tokens and $0.14 per million output tokens ($0.21 blended 1M-in + 1M-out). Inkling-Small costs $0.30 / $1.20 per million tokens ($1.50 blended). Sources: https://thinkingmachines.ai and https://azure.microsoft.com/pricing/details/phi-3/. The cheapest LLM for your app still depends on how many output tokens you generate.

    How much does Inkling-Small vs Phi-3.5-vision-instruct cost per million tokens?

    Inkling-Small Thinking Machines Lab API pricing is $0.30 input and $1.20 output per million tokens via Thinking Machines Lab. Phi-3.5-vision-instruct Microsoft API pricing is $0.07 input and $0.14 output per million tokens via Microsoft. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.

    Which is better for coding, Inkling-Small or Phi-3.5-vision-instruct?

    Inkling-Small has a published SWE-bench Verified score of 80.2%. Phi-3.5-vision-instruct does not have that eval on this page yet.

    What is the context window for Inkling-Small vs Phi-3.5-vision-instruct?

    Inkling-Small supports a 256K token context window, while Phi-3.5-vision-instruct supports 128K tokens. Inkling-Small offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.

    Which model performs better on benchmarks, Inkling-Small or Phi-3.5-vision-instruct?

    Shared benchmark scores for Inkling-Small and Phi-3.5-vision-instruct are still limited. Check the comparison table for the evals each model has published. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.

    Is Inkling-Small or Phi-3.5-vision-instruct better for production use?

    Both Inkling-Small and Phi-3.5-vision-instruct are production API models. For cost-sensitive production traffic, Phi-3.5-vision-instruct has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.

    Can I switch between Inkling-Small and Phi-3.5-vision-instruct in my app?

    Yes. Call Inkling-Small through Thinking Machines Lab and Phi-3.5-vision-instruct through Microsoft with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.

    How accurate is this Inkling-Small vs Phi-3.5-vision-instruct pricing data?

    List rates are the latest published Thinking Machines Lab API pricing and Microsoft API pricing, quoted per million tokens. Official rate sheets: https://thinkingmachines.ai and https://azure.microsoft.com/pricing/details/phi-3/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.

    What is the output token limit for Inkling-Small and Phi-3.5-vision-instruct?

    Inkling-Small supports up to 256K output tokens per request, while Phi-3.5-vision-instruct supports up to an unspecified number of output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.

    Which model has better throughput, Inkling-Small or Phi-3.5-vision-instruct?

    Neither Inkling-Small nor Phi-3.5-vision-instruct has published throughput data on this page yet. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.

    How do I switch the models in this Inkling-Small vs Phi-3.5-vision-instruct comparison?

    Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Inkling-Small or Phi-3.5-vision-instruct from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.

    Inkling-Small vs Phi-3.5-vision-instruct pricing

    This comparison covers API pricing, context window, throughput, and benchmark scores. Inkling-Small costs $0.30/M input and $1.20/M output via Thinking Machines Lab. Phi-3.5-vision-instruct costs $0.07/M input and $0.14/M output.

    Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.

    The index

    All Large Language Models

    343 models across 36 providers. Search or jump to a lab — every model page stays linked here.

    Baidu

    2 models

    Inception

    1 models

    inclusionAI

    1 models

    LG AI Research

    1 models

    Liquid AI

    2 models

    Nous Research

    1 models

    OpenBMB

    1 models

    Sakana AI

    1 models

    Sarvam AI

    2 models

    Tencent

    1 models

    Thinking Machines

    0 models

    Unisound

    1 models

    Upstage

    1 models

    Next step

    You found the model. Now ship the product.

    Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.