DeepSeek OCR 2 vs GLM-4.7-FlashX vs Step 3.5 Flash
Too close to call on our weighted score (Step 3.5 Flash 62, GLM-4.7-FlashX 61, DeepSeek OCR 2 32). The right pick depends on what you value most.
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
Z.ai (Zhipu)GLM-4.7-FlashX
61/100- ECI—
- Price$0.07 / $0.40
- Context200K
StepFunStep 3.5 Flash
62/100- ECI—
- Price$0.10 / $0.30
- Context256K
Too close to call
It is close. Our weighted score puts them within 1 points (Step 3.5 Flash 62/100, GLM-4.7-FlashX 61/100, DeepSeek OCR 2 32/100), so choose by what matters most for your work: Step 3.5 Flash on price and Step 3.5 Flash for long inputs. 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 OCR 2 $1.03 per 1M tokens (3:1 blend)
- Longest contextStep 3.5 FlashStep 3.5 Flash 256,000 · GLM-4.7-FlashX 200,000 · DeepSeek OCR 2 8,192 tokens
- Widest inputsDeepSeek OCR 2DeepSeek OCR 2: Text, Images · GLM-4.7-FlashX: Text · Step 3.5 Flash: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek OCR 2 | GLM-4.7-FlashX | Step 3.5 Flash |
|---|---|---|---|---|
| Price | 50% | 49 | 89 | 89 |
| Inputs & features | 30% | 25 | 35 | 35 |
| Context window | 20% | 0 | 32 | 36 |
| Overall | 100% | 32/100 | 61/100 | 62/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek OCR 2DeepSeek | GLM-4.7-FlashXZ.ai (Zhipu) | Step 3.5 FlashStepFun |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.89 | $0.07 (best) | $0.10 |
| Output | $1.47 | $0.40 | $0.30 (best) |
| Cached input | — | $0.01 (best) | $0.02 |
| Blended (3:1) | $1.03 | $0.152 | $0.15 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Z.AI API | Official StepFun (Global) API |
| Limits | |||
| Context window | 8,192 tokens | 200,000 tokens | 256,000 tokens (best) |
| Max output | 8,192 tokens | 131,072 tokens | 256,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yeslow · high |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | glm-4.7-flashx | step-3.5-flash |
| API providers | 2 | 8 (best) | 8 (best) |
| Released | Jan 27, 2026 | Jan 19, 2026 | Jan 29, 2026 |
| Knowledge cutoff | — | Apr 2025 | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek OCR 2$11.83
- GLM-4.7-FlashX$1.50
- Step 3.5 Flash$1.60
Which should you choose?
Which is better: DeepSeek OCR 2, GLM-4.7-FlashX or Step 3.5 Flash?
It is close. Our weighted score puts them within 1 points (Step 3.5 Flash 62/100, GLM-4.7-FlashX 61/100, DeepSeek OCR 2 32/100), so choose by what matters most for your work: Step 3.5 Flash on price and Step 3.5 Flash for long inputs. 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, DeepSeek OCR 2, GLM-4.7-FlashX 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 OCR 2 costs $0.89 input / $1.47 output per million tokens (median across 1 API provider). 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 $1.03 for DeepSeek OCR 2 (6.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek OCR 2 has not been scored yet, GLM-4.7-FlashX has not been scored yet and Step 3.5 Flash has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek OCR 2, GLM-4.7-FlashX and Step 3.5 Flash yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DeepSeek OCR 2 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 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, GLM-4.7-FlashX up to 131,072, Step 3.5 Flash up to 256,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek OCR 2 accepts text and images; GLM-4.7-FlashX accepts text; Step 3.5 Flash accepts text. DeepSeek OCR 2 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Step 3.5 Flash is the newest, released Jan 29, 2026. DeepSeek OCR 2 came out Jan 27, 2026; GLM-4.7-FlashX came out Jan 19, 2026. Knowledge cutoff: GLM-4.7-FlashX Apr 2025, Step 3.5 Flash Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.
