ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.7-FlashX vs DeepSeek V4 Flash 0731 vs Step 3.5 Flash

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. Z.ai (Zhipu)

    GLM-4.7-FlashX

    Released Jan 19, 2026

    61/100
    • ECI—
    • Price$0.07 / $0.40
    • Context200K
  2. DeepSeek

    DeepSeek V4 Flash 0731

    Released Jul 31, 2026

    64/100
    • ECI154.4
    • Price$0.14 / $0.30
    • Context1M
  3. StepFun

    Step 3.5 Flash

    Released Jan 29, 2026

    65/100
    • ECI—
    • Price$0.10 / $0.30
    • Context256K
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, DeepSeek V4 Flash 0731 64/100, GLM-4.7-FlashX 61/100) 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 priceStep 3.5 FlashStep 3.5 Flash $0.15 · GLM-4.7-FlashX $0.152 · DeepSeek V4 Flash 0731 $0.18 per 1M tokens (3:1 blend)
  • Longest contextDeepSeek V4 Flash 0731DeepSeek V4 Flash 0731 1,000,000 · Step 3.5 Flash 256,000 · GLM-4.7-FlashX 200,000 tokens
  • Widest inputsSame inputsGLM-4.7-FlashX: Text · DeepSeek V4 Flash 0731: Text · Step 3.5 Flash: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGLM-4.7-FlashXDeepSeek V4 Flash 0731Step 3.5 Flash
Price50%858285
Inputs & features30%353545
Context window20%396443
Specs & price only100%61/10064/10065/100

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.

GLM-4.7-FlashX vs DeepSeek V4 Flash 0731 vs Step 3.5 Flash specifications side by side
SpecificationGLM-4.7-FlashXZ.ai (Zhipu)DeepSeek V4 Flash 0731DeepSeekStep 3.5 FlashStepFun
Capability
Capabilities Index (ECI)—154.4—
ECI rank—#52 of 158—
GPQA DiamondGraduate-level science questions—91.0%—
FrontierMath Tiers 1–3Research-level mathematics—57.5%—
OTIS Mock AIME 2024–2025Competition mathematics—94.4%—
SimpleQA VerifiedShort factual questions—33.6%—
Price per million tokens
Input$0.07 (best)$0.14$0.10
Output$0.40$0.30 (best)$0.30 (best)
Cached input$0.01 (best)—$0.02
Blended (3:1)$0.152$0.18$0.15 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIMedian of 65 providersOfficial StepFun (Global) API
Limits
Context window200,000 tokens1,000,000 tokens (best)256,000 tokens
Max output131,072 tokens384,000 tokens (best)256,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYeslow · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenMITOpen
API model IDglm-4.7-flashx—step-3.5-flash
API providers1066 (best)11
ReleasedJan 19, 2026Jul 31, 2026Jan 29, 2026
Knowledge cutoffApr 2025May 2025Jan 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.

  • GLM-4.7-FlashX$1.50
  • DeepSeek V4 Flash 0731$2.00
  • Step 3.5 Flash$1.60
04 — Questions

Which should you choose?

Which is better: GLM-4.7-FlashX, DeepSeek V4 Flash 0731 or Step 3.5 Flash?

There is not enough shared capability evidence to name an overall winner. The scores (Step 3.5 Flash 65/100, DeepSeek V4 Flash 0731 64/100, GLM-4.7-FlashX 61/100) 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, GLM-4.7-FlashX, DeepSeek V4 Flash 0731 or Step 3.5 Flash?

Step 3.5 Flash is cheaper at $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); DeepSeek V4 Flash 0731 costs $0.14 input / $0.30 output per million tokens (median across 65 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Step 3.5 Flash versus $0.152 for GLM-4.7-FlashX (1× as much) and $0.18 for DeepSeek V4 Flash 0731 (1.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GLM-4.7-FlashX has not been scored yet, DeepSeek V4 Flash 0731 has an ECI of 154.4 and Step 3.5 Flash has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7-FlashX, DeepSeek V4 Flash 0731 and Step 3.5 Flash yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

DeepSeek V4 Flash 0731 has the largest context window at 1,000,000 tokens, against 256,000 for Step 3.5 Flash and 200,000 for GLM-4.7-FlashX. Maximum output per response: GLM-4.7-FlashX up to 131,072, DeepSeek V4 Flash 0731 up to 384,000, Step 3.5 Flash up to 256,000 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7-FlashX accepts text; DeepSeek V4 Flash 0731 accepts text; Step 3.5 Flash accepts text. They handle the same number of input types.

Are any of these open source?

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

Which is newer?

DeepSeek V4 Flash 0731 is the newest, released Jul 31, 2026. Step 3.5 Flash came out Jan 29, 2026; GLM-4.7-FlashX came out Jan 19, 2026. Knowledge cutoff: GLM-4.7-FlashX Apr 2025, DeepSeek V4 Flash 0731 May 2025, Step 3.5 Flash Jan 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.