ZMIME
Comparison · 3 models · Updated Nov 18, 2026

LightOnOCR 2 1B vs Step 3.5 Flash vs GLM-4.7-FlashX

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. LightOn

    LightOnOCR 2 1B

    Released Jan 16, 2026

    52/100
    • ECI—
    • Price$0.101 / $0.209
    • Context16K
  2. StepFun

    Step 3.5 Flash

    Released Jan 29, 2026

    65/100
    • ECI—
    • Price$0.10 / $0.30
    • Context256K
  3. Z.ai (Zhipu)

    GLM-4.7-FlashX

    Released Jan 19, 2026

    61/100
    • ECI—
    • Price$0.07 / $0.40
    • Context200K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Step 3.5 Flash 65/100, GLM-4.7-FlashX 61/100, LightOnOCR 2 1B 52/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceLightOnOCR 2 1BLightOnOCR 2 1B $0.128 · Step 3.5 Flash $0.15 · GLM-4.7-FlashX $0.152 per 1M tokens (3:1 blend)
  • Longest contextStep 3.5 FlashStep 3.5 Flash 256,000 · GLM-4.7-FlashX 200,000 · LightOnOCR 2 1B 16,384 tokens
  • Widest inputsLightOnOCR 2 1BLightOnOCR 2 1B: Text, Images · Step 3.5 Flash: Text · GLM-4.7-FlashX: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLightOnOCR 2 1BStep 3.5 FlashGLM-4.7-FlashX
Price50%888585
Inputs & features30%254535
Context window20%04339
Specs & price only100%52/10065/10061/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

LightOnOCR 2 1B vs Step 3.5 Flash vs GLM-4.7-FlashX specifications side by side
SpecificationLightOnOCR 2 1BLightOnStep 3.5 FlashStepFunGLM-4.7-FlashXZ.ai (Zhipu)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.101$0.10$0.07 (best)
Output$0.209 (best)$0.30$0.40
Cached input—$0.02$0.01 (best)
Blended (3:1)$0.128 (best)$0.15$0.152
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 2 providersOfficial StepFun (Global) APIOfficial Z.AI API
Limits
Context window16,384 tokens256,000 tokens (best)200,000 tokens
Max output—256,000 tokens (best)131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYeslow · highYes
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenapache-2.0OpenOpen
API model ID—step-3.5-flashglm-4.7-flashx
API providers211 (best)10
ReleasedJan 16, 2026Jan 29, 2026Jan 19, 2026
Knowledge cutoff—Jan 2025Apr 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • LightOnOCR 2 1B$1.43
  • Step 3.5 Flash$1.60
  • GLM-4.7-FlashX$1.50
04 — Questions

Which should you choose?

Which is better: LightOnOCR 2 1B, Step 3.5 Flash or GLM-4.7-FlashX?

There is not enough shared capability evidence to name an overall winner. The scores (Step 3.5 Flash 65/100, GLM-4.7-FlashX 61/100, LightOnOCR 2 1B 52/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, LightOnOCR 2 1B, Step 3.5 Flash or GLM-4.7-FlashX?

LightOnOCR 2 1B is cheaper at $0.101 input / $0.209 output per million tokens (median across 2 API providers). Step 3.5 Flash costs $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price); GLM-4.7-FlashX costs $0.07 input / $0.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.128 per million tokens for LightOnOCR 2 1B versus $0.15 for Step 3.5 Flash (1.2× as much) and $0.152 for GLM-4.7-FlashX (1.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. LightOnOCR 2 1B has not been scored yet, Step 3.5 Flash has not been scored yet and GLM-4.7-FlashX has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for LightOnOCR 2 1B, Step 3.5 Flash and GLM-4.7-FlashX yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that LightOnOCR 2 1B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Step 3.5 Flash has the largest context window at 256,000 tokens, against 200,000 for GLM-4.7-FlashX and 16,384 for LightOnOCR 2 1B. Maximum output per response: Step 3.5 Flash up to 256,000, GLM-4.7-FlashX up to 131,072 tokens.

Which can read images, PDFs, audio or video?

LightOnOCR 2 1B accepts text and images; Step 3.5 Flash accepts text; GLM-4.7-FlashX accepts text. LightOnOCR 2 1B handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (apache-2.0), so you can self-host them.

Which is newer?

Step 3.5 Flash is the newest, released Jan 29, 2026. GLM-4.7-FlashX came out Jan 19, 2026; LightOnOCR 2 1B came out Jan 16, 2026. Knowledge cutoff: Step 3.5 Flash Jan 2025, GLM-4.7-FlashX Apr 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.