DeepSeek V4 Flash Vision Exp vs Muse Glimmer 30B vs Ornith 1.5 35B A3B
DeepSeek V4 Flash Vision Exp comes out ahead, 70 to 59 and 57 on our weighted score, and it is the cheaper option too.
- Our pick
DeepSeekDeepSeek V4 Flash Vision Exp
70/100- ECI—
- Price$0.216 / $0.647
- Context1M
MetaMuse Glimmer 30B
57/100- ECI—
- Price$0.30 / $1.20
- Context131K
DeepReinforce
Ornith 1.5 35B A3B
59/100- ECI—
- Price$0.20 / $1.70
- Context262K
DeepSeek V4 Flash Vision Exp is our pick
DeepSeek V4 Flash Vision Exp is the better all-round choice, scoring 70/100 against Ornith 1.5 35B A3B (59) and Muse Glimmer 30B (57). It leads on price and context window. 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 priceDeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp $0.323 · Muse Glimmer 30B $0.525 · Ornith 1.5 35B A3B $0.575 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp 1,000,000 · Ornith 1.5 35B A3B 262,144 · Muse Glimmer 30B 131,072 tokens
- Widest inputsSame inputsDeepSeek V4 Flash Vision Exp: Text, Images · Muse Glimmer 30B: Text, Images · Ornith 1.5 35B A3B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek V4 Flash Vision Exp | Muse Glimmer 30B | Ornith 1.5 35B A3B |
|---|---|---|---|---|
| Price | 50% | 73 | 63 | 61 |
| Inputs & features | 30% | 70 | 70 | 70 |
| Context window | 20% | 60 | 24 | 37 |
| Overall | 100% | 70/100 | 57/100 | 59/100 |
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 Flash Vision ExpDeepSeek | Muse Glimmer 30BMeta | Ornith 1.5 35B A3BDeepReinforce |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.216 | $0.30 | $0.20 (best) |
| Output | $0.647 (best) | $1.20 | $1.70 |
| Cached input | — | — | — |
| Blended (3:1) | $0.323 (best) | $0.525 | $0.575 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 15 providers | Median of 10 providers | Median of 2 providers |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 131,072 tokens | 262,144 tokens |
| Max output | 384,000 tokens (best) | 131,072 tokens | — |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | OpenApache 2.0 | OpenMIT |
| API model ID | — | — | — |
| API providers | 15 (best) | 12 | 2 |
| Released | Aug 21, 2026 | Aug 10, 2026 | Aug 18, 2026 |
| Knowledge cutoff | — | Jan 4, 2026 | — |
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 Flash Vision Exp$3.45
- Muse Glimmer 30B$5.40
- Ornith 1.5 35B A3B$5.40
Which should you choose?
Which is better: DeepSeek V4 Flash Vision Exp, Muse Glimmer 30B or Ornith 1.5 35B A3B?
DeepSeek V4 Flash Vision Exp is the better all-round choice, scoring 70/100 against Ornith 1.5 35B A3B (59) and Muse Glimmer 30B (57). It leads on price and context window. 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 Flash Vision Exp, Muse Glimmer 30B or Ornith 1.5 35B A3B?
DeepSeek V4 Flash Vision Exp is cheaper at $0.216 input / $0.647 output per million tokens (median across 15 API providers). Muse Glimmer 30B costs $0.30 input / $1.20 output per million tokens (median across 10 API providers); Ornith 1.5 35B A3B costs $0.20 input / $1.70 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.323 per million tokens for DeepSeek V4 Flash Vision Exp versus $0.525 for Muse Glimmer 30B (1.6× as much) and $0.575 for Ornith 1.5 35B A3B (1.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek V4 Flash Vision Exp has not been scored yet, Muse Glimmer 30B has not been scored yet and Ornith 1.5 35B A3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Flash Vision Exp, Muse Glimmer 30B and Ornith 1.5 35B A3B 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 Vision Exp has the largest context window at 1,000,000 tokens, against 262,144 for Ornith 1.5 35B A3B and 131,072 for Muse Glimmer 30B. Maximum output per response: DeepSeek V4 Flash Vision Exp up to 384,000, Muse Glimmer 30B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Flash Vision Exp accepts text and images; Muse Glimmer 30B accepts text and images; Ornith 1.5 35B A3B accepts text and images. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (MIT and Apache 2.0), so you can self-host them.
Which is newer?
DeepSeek V4 Flash Vision Exp is the newest, released Aug 21, 2026. Ornith 1.5 35B A3B came out Aug 18, 2026; Muse Glimmer 30B came out Aug 10, 2026. Knowledge cutoff: Muse Glimmer 30B Jan 4, 2026.
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.
