Mercury 2.5 vs Beam 1.0 501B A23B vs DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp comes out ahead, 65 to 55 and 54 on our weighted score, and it is the cheaper option too.
InceptionMercury 2.5
55/100- ECI—
- Price$0.20 / $0.75
- Context260K
Reflection AIBeam 1.0 501B A23B
54/100- ECI—
- Price$0.30 / $1.00
- Context1.05M
- Our pick
DeepSeekDeepSeek V4 Flash Vision Exp
65/100- ECI—
- Price$0.216 / $0.647
- Context1M
DeepSeek V4 Flash Vision Exp is our pick
DeepSeek V4 Flash Vision Exp is the better all-round choice, scoring 65/100 against Mercury 2.5 (55) and Beam 1.0 501B A23B (54). It leads on inputs & features. 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 · Mercury 2.5 $0.338 · Beam 1.0 501B A23B $0.475 per 1M tokens (3:1 blend)
- Longest contextBeam 1.0 501B A23BBeam 1.0 501B A23B 1,048,576 · DeepSeek V4 Flash Vision Exp 1,000,000 · Mercury 2.5 260,000 tokens
- Widest inputsDeepSeek V4 Flash Vision ExpMercury 2.5: Text · Beam 1.0 501B A23B: Text · DeepSeek V4 Flash Vision Exp: Text, Images
- Self-hostingBeam 1.0 501B A23B and DeepSeek V4 Flash Vision ExpPublishes downloadable weights (Apache-2.0 and MIT)
| Measure | Weight | Mercury 2.5 | Beam 1.0 501B A23B | DeepSeek V4 Flash Vision Exp |
|---|---|---|---|---|
| Price | 50% | 69 | 62 | 70 |
| Inputs & features | 30% | 45 | 35 | 60 |
| Context window | 20% | 36 | 61 | 60 |
| Overall | 100% | 55/100 | 54/100 | 65/100 |
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 | Mercury 2.5Inception | Beam 1.0 501B A23BReflection AI | DeepSeek V4 Flash Vision ExpDeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.20 (best) | $0.30 | $0.216 |
| Output | $0.75 | $1.00 | $0.647 (best) |
| Cached input | $0.02 | — | — |
| Blended (3:1) | $0.338 | $0.475 | $0.323 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Inception API | Median of 7 providers | Median of 14 providers |
| Limits | |||
| Context window | 260,000 tokens | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max output | 65,536 tokens | 131,072 tokens | 384,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | OpenMIT |
| API model ID | mercury-2.5 | — | — |
| API providers | 6 | 12 | 15 (best) |
| Released | Sep 8, 2026 | Oct 5, 2026 | Aug 21, 2026 |
| Knowledge cutoff | — | Jun 30, 2026 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mercury 2.5$3.50
- Beam 1.0 501B A23B$5.00
- DeepSeek V4 Flash Vision Exp$3.45
Which should you choose?
Which is better: Mercury 2.5, Beam 1.0 501B A23B or DeepSeek V4 Flash Vision Exp?
DeepSeek V4 Flash Vision Exp is the better all-round choice, scoring 65/100 against Mercury 2.5 (55) and Beam 1.0 501B A23B (54). It leads on inputs & features. 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, Mercury 2.5, Beam 1.0 501B A23B or DeepSeek V4 Flash Vision Exp?
DeepSeek V4 Flash Vision Exp is cheaper at $0.216 input / $0.647 output per million tokens (median across 14 API providers). Mercury 2.5 costs $0.20 input / $0.75 output per million tokens (official Inception API price); Beam 1.0 501B A23B costs $0.30 input / $1.00 output per million tokens (median across 7 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 $0.338 for Mercury 2.5 (1× as much) and $0.475 for Beam 1.0 501B A23B (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mercury 2.5 has not been scored yet, Beam 1.0 501B A23B has not been scored yet and DeepSeek V4 Flash Vision Exp has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Mercury 2.5, Beam 1.0 501B A23B and DeepSeek V4 Flash Vision Exp 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?
Beam 1.0 501B A23B has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Flash Vision Exp and 260,000 for Mercury 2.5. Maximum output per response: Mercury 2.5 up to 65,536, Beam 1.0 501B A23B up to 131,072, DeepSeek V4 Flash Vision Exp up to 384,000 tokens.
Which can read images, PDFs, audio or video?
Mercury 2.5 accepts text; Beam 1.0 501B A23B accepts text; DeepSeek V4 Flash Vision Exp accepts text and images. DeepSeek V4 Flash Vision Exp handles the widest range of inputs.
Are any of these open source?
Beam 1.0 501B A23B and DeepSeek V4 Flash Vision Exp publishes its weights (Apache-2.0 and MIT) and can be self-hosted; Mercury 2.5 is proprietary.
Which is newer?
Beam 1.0 501B A23B is the newest, released Oct 5, 2026. Mercury 2.5 came out Sep 8, 2026; DeepSeek V4 Flash Vision Exp came out Aug 21, 2026. Knowledge cutoff: Beam 1.0 501B A23B Jun 30, 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 Nov 2, 2026.
