MiniCPM5-2B vs GPT-6 Astra (Fast) vs Mercury 2.5
GPT-6 Astra (Fast) comes out ahead, 66 to 42 and 31 on our weighted score, though Mercury 2.5 is 119× cheaper per token.
OpenBMB
MiniCPM5-2B
31/100- ECI—
- Price—
- Context131K
- Our pick
OpenAIGPT-6 Astra (Fast)
66/100- ECI—
- Price$20.00 / $100.00
- Context1.05M
InceptionMercury 2.5
42/100- ECI—
- Price$0.20 / $0.75
- Context260K
GPT-6 Astra (Fast) is our pick
GPT-6 Astra (Fast) is the better all-round choice, scoring 66/100 against Mercury 2.5 (42) and MiniCPM5-2B (31). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. 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 priceMercury 2.5Mercury 2.5 $0.338 · GPT-6 Astra (Fast) $40.00 per 1M tokens (3:1 blend) · MiniCPM5-2B unpriced
- Longest contextGPT-6 Astra (Fast)GPT-6 Astra (Fast) 1,050,000 · Mercury 2.5 260,000 · MiniCPM5-2B 131,072 tokens
- Widest inputsGPT-6 Astra (Fast)MiniCPM5-2B: Text · GPT-6 Astra (Fast): Text, Images, PDFs · Mercury 2.5: Text
- Self-hostingMiniCPM5-2BPublishes downloadable weights (apache-2.0)
| Measure | Weight | MiniCPM5-2B | GPT-6 Astra (Fast) | Mercury 2.5 |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 70 | 45 |
| Context window | 40% | 25 | 61 | 36 |
| Overall | 100% | 31/100 | 66/100 | 42/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiniCPM5-2BOpenBMB | GPT-6 Astra (Fast)OpenAI | Mercury 2.5Inception |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | $20.00 | $0.20 (best) |
| Output | — | $100.00 | $0.75 (best) |
| Cached input | — | — | $0.02 |
| Blended (3:1) | — | $40.00 | $0.338 (best) |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 1 providers | Official Inception API |
| Limits | |||
| Context window | 131,072 tokens | 1,050,000 tokens (best) | 260,000 tokens |
| Max output | 131,072 tokens (best) | 128,000 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Openapache-2.0 | Proprietary | Proprietary |
| API model ID | — | — | mercury-2.5 |
| API providers | 1 | 1 | 6 (best) |
| Released | Sep 6, 2026 | Sep 4, 2026 | Sep 8, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiniCPM5-2B—
- GPT-6 Astra (Fast)$400.00
- Mercury 2.5$3.50
Which should you choose?
Which is better: MiniCPM5-2B, GPT-6 Astra (Fast) or Mercury 2.5?
GPT-6 Astra (Fast) is the better all-round choice, scoring 66/100 against Mercury 2.5 (42) and MiniCPM5-2B (31). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MiniCPM5-2B, GPT-6 Astra (Fast) or Mercury 2.5?
Mercury 2.5 is cheaper at $0.20 input / $0.75 output per million tokens (official Inception API price). GPT-6 Astra (Fast) costs $20.00 input / $100.00 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.338 per million tokens for Mercury 2.5 versus $40.00 for GPT-6 Astra (Fast) (119× as much). MiniCPM5-2B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniCPM5-2B has not been scored yet, GPT-6 Astra (Fast) has not been scored yet and Mercury 2.5 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniCPM5-2B, GPT-6 Astra (Fast) and Mercury 2.5 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?
GPT-6 Astra (Fast) has the largest context window at 1,050,000 tokens, against 260,000 for Mercury 2.5 and 131,072 for MiniCPM5-2B. Maximum output per response: MiniCPM5-2B up to 131,072, GPT-6 Astra (Fast) up to 128,000, Mercury 2.5 up to 65,536 tokens.
Which can read images, PDFs, audio or video?
MiniCPM5-2B accepts text; GPT-6 Astra (Fast) accepts text, images and PDFs; Mercury 2.5 accepts text. GPT-6 Astra (Fast) handles the widest range of inputs.
Are any of these open source?
MiniCPM5-2B publishes its weights (apache-2.0) and can be self-hosted; GPT-6 Astra (Fast) and Mercury 2.5 is proprietary.
Which is newer?
Mercury 2.5 is the newest, released Sep 8, 2026. MiniCPM5-2B came out Sep 6, 2026; GPT-6 Astra (Fast) came out Sep 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 Nov 2, 2026.
