Qwen-VL Max vs Codestral vs Sonar
Codestral comes out ahead, 48 to 41 and 30 on our weighted score, and it is the cheaper option too.
Alibaba (Qwen)Qwen-VL Max
41/100- ECI—
- Price$0.80 / $3.20
- Context131K
- Our pick
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
PerplexitySonar
30/100- ECI—
- Price$1.00 / $1.00
- Context128K
Codestral is our pick
Codestral is the better all-round choice, scoring 48/100 against Qwen-VL Max (41) and Sonar (30). It leads on price and context window. Qwen-VL Max wins 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 priceCodestralCodestral $0.45 · Sonar $1.00 · Qwen-VL Max $1.40 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Qwen-VL Max 131,072 · Sonar 128,000 tokens
- Widest inputsQwen-VL MaxQwen-VL Max: Text, Images · Codestral: Text · Sonar: Text
- Self-hostingCodestralPublishes downloadable weights
| Measure | Weight | Qwen-VL Max | Codestral | Sonar |
|---|---|---|---|---|
| Price | 50% | 43 | 66 | 50 |
| Inputs & features | 30% | 50 | 25 | 0 |
| Context window | 20% | 24 | 36 | 24 |
| Overall | 100% | 41/100 | 48/100 | 30/100 |
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 | Qwen-VL MaxAlibaba (Qwen) | CodestralMistral AI | SonarPerplexity |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.80 | $0.30 (best) | $1.00 |
| Output | $3.20 | $0.90 (best) | $1.00 |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $1.40 | $0.45 (best) | $1.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Mistral API | Official Perplexity API |
| Limits | |||
| Context window | 131,072 tokens | 256,000 tokens (best) | 128,000 tokens |
| Max output | 8,192 tokens (best) | 4,096 tokens | 4,096 tokens |
| 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 | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | qwen-vl-max | codestral-latest | sonar |
| API providers | 3 | 3 | 6 (best) |
| Released | Apr 8, 2024 | May 29, 2024 | Jan 1, 2024 |
| Knowledge cutoff | Apr 2024 | Oct 2024 | Sep 1, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen-VL Max$14.40
- Codestral$4.80
- Sonar$12.00
Which should you choose?
Which is better: Qwen-VL Max, Codestral or Sonar?
Codestral is the better all-round choice, scoring 48/100 against Qwen-VL Max (41) and Sonar (30). It leads on price and context window. Qwen-VL Max wins 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, Qwen-VL Max, Codestral or Sonar?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Sonar costs $1.00 input / $1.00 output per million tokens (official Perplexity API price); Qwen-VL Max costs $0.80 input / $3.20 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $1.00 for Sonar (2.2× as much) and $1.40 for Qwen-VL Max (3.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen-VL Max has not been scored yet, Codestral has not been scored yet and Sonar has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen-VL Max, Codestral and Sonar yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar does not support tool calling, which most coding agents need.
Which has the bigger context window?
Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen-VL Max and 128,000 for Sonar. Maximum output per response: Qwen-VL Max up to 8,192, Codestral up to 4,096, Sonar up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Qwen-VL Max accepts text and images; Codestral accepts text; Sonar accepts text. Qwen-VL Max handles the widest range of inputs.
Are any of these open source?
Codestral publishes its weights and can be self-hosted; Qwen-VL Max and Sonar is proprietary.
Which is newer?
Codestral is the newest, released May 29, 2024. Qwen-VL Max came out Apr 8, 2024; Sonar came out Jan 1, 2024. Knowledge cutoff: Qwen-VL Max Apr 2024, Codestral Oct 2024, Sonar Sep 1, 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.
