DeepSeek V4 Pro vs GLM-5V-Turbo vs Sakana Namazu
Too close to call on our weighted score (Sakana Namazu 51, GLM-5V-Turbo 49, DeepSeek V4 Pro 45). The right pick depends on what you value most.
DeepSeekDeepSeek V4 Pro
45/100- ECI—
- Price$1.32 / $3.00
- Context1M
Z.ai (Zhipu)GLM-5V-Turbo
49/100- ECI—
- Price$1.20 / $4.00
- Context200K
Sakana AI
Sakana Namazu
51/100- ECI—
- Price$0.95 / $4.00
- Context262K
Too close to call
It is close. Our weighted score puts them within 2 points (Sakana Namazu 51/100, GLM-5V-Turbo 49/100, DeepSeek V4 Pro 45/100), so choose by what matters most for your work: Sakana Namazu on price and DeepSeek V4 Pro 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 priceSakana NamazuSakana Namazu $1.71 · DeepSeek V4 Pro $1.74 · GLM-5V-Turbo $1.90 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 ProDeepSeek V4 Pro 1,000,000 · Sakana Namazu 262,144 · GLM-5V-Turbo 200,000 tokens
- Widest inputsGLM-5V-TurboDeepSeek V4 Pro: Text · GLM-5V-Turbo: Text, Images, PDFs, Video · Sakana Namazu: Text, Images, PDFs
- Self-hostingDeepSeek V4 ProPublishes downloadable weights
| Measure | Weight | DeepSeek V4 Pro | GLM-5V-Turbo | Sakana Namazu |
|---|---|---|---|---|
| Price | 50% | 38 | 37 | 39 |
| Inputs & features | 30% | 45 | 80 | 80 |
| Context window | 20% | 60 | 32 | 37 |
| Overall | 100% | 45/100 | 49/100 | 51/100 |
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 V4 ProDeepSeek | GLM-5V-TurboZ.ai (Zhipu) | Sakana NamazuSakana AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.32 | $1.20 | $0.95 (best) |
| Output | $3.00 (best) | $4.00 | $4.00 |
| Cached input | — | $0.24 | $0.15 (best) |
| Blended (3:1) | $1.74 | $1.90 | $1.71 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 49 providers | Official Z.AI API | Official Sakana AI API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 200,000 tokens | 262,144 tokens |
| Max output | 384,000 tokens (best) | 131,072 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | glm-5v-turbo | sakana-namazu |
| API providers | 52 (best) | 14 | 5 |
| Released | Apr 24, 2026 | Apr 1, 2026 | Aug 3, 2026 |
| Knowledge cutoff | May 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 V4 Pro$19.20
- GLM-5V-Turbo$20.00
- Sakana Namazu$17.50
Which should you choose?
Which is better: DeepSeek V4 Pro, GLM-5V-Turbo or Sakana Namazu?
It is close. Our weighted score puts them within 2 points (Sakana Namazu 51/100, GLM-5V-Turbo 49/100, DeepSeek V4 Pro 45/100), so choose by what matters most for your work: Sakana Namazu on price and DeepSeek V4 Pro 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 V4 Pro, GLM-5V-Turbo or Sakana Namazu?
Sakana Namazu is cheaper at $0.95 input / $4.00 output per million tokens (official Sakana AI API price). DeepSeek V4 Pro costs $1.32 input / $3.00 output per million tokens (median across 49 API providers); GLM-5V-Turbo costs $1.20 input / $4.00 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $1.71 per million tokens for Sakana Namazu versus $1.74 for DeepSeek V4 Pro (1× as much) and $1.90 for GLM-5V-Turbo (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek V4 Pro has not been scored yet, GLM-5V-Turbo has not been scored yet and Sakana Namazu has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Pro, GLM-5V-Turbo and Sakana Namazu 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 Pro has the largest context window at 1,000,000 tokens, against 262,144 for Sakana Namazu and 200,000 for GLM-5V-Turbo. Maximum output per response: DeepSeek V4 Pro up to 384,000, GLM-5V-Turbo up to 131,072, Sakana Namazu up to 65,536 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro accepts text; GLM-5V-Turbo accepts text, images, PDFs and video; Sakana Namazu accepts text, images and PDFs. GLM-5V-Turbo handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro publishes its weights and can be self-hosted; GLM-5V-Turbo and Sakana Namazu is proprietary.
Which is newer?
Sakana Namazu is the newest, released Aug 3, 2026. DeepSeek V4 Pro came out Apr 24, 2026; GLM-5V-Turbo came out Apr 1, 2026. Knowledge cutoff: DeepSeek V4 Pro May 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.
