Codestral vs Qwen Max
Codestral comes out ahead, 48 to 22 on our weighted score, and it is the cheaper option too.
Codestral is our pick
Codestral is the better all-round choice, scoring 48/100 against Qwen Max (22). 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 priceCodestralCodestral $0.45 · Qwen Max $2.80 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Qwen Max 32,768 tokens
- Widest inputsSame inputsCodestral: Text · Qwen Max: Text
- Self-hostingCodestralPublishes downloadable weights
| Measure | Weight | Codestral | Qwen Max |
|---|---|---|---|
| Price | 50% | 66 | 29 |
| Inputs & features | 30% | 25 | 25 |
| Context window | 20% | 36 | 0 |
| Overall | 100% | 48/100 | 22/100 |
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 |  CodestralMistral AI |  Qwen MaxAlibaba (Qwen) |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | $0.30 (best) | $1.60 |
| Output | $0.90 (best) | $6.40 |
| Cached input | $0.03 | — |
| Blended (3:1) | $0.45 (best) | $2.80 |
| Long-context rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Alibaba API |
| Limits | ||
| Context window | 256,000 tokens (best) | 32,768 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | No | No |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Open | Proprietary |
| API model ID | codestral-latest | qwen-max |
| API providers | 3 | 6 (best) |
| Released | May 29, 2024 | Apr 3, 2024 |
| Knowledge cutoff | Oct 2024 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral$4.80
- Qwen Max$28.80
Which should you choose?
Which is better: Codestral or Qwen Max?
Codestral is the better all-round choice, scoring 48/100 against Qwen Max (22). 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, Codestral or Qwen Max?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen Max costs $1.60 input / $6.40 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 $2.80 for Qwen Max (6.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Codestral has not been scored yet and Qwen Max has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral and Qwen Max yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.
Which has the bigger context window?
Codestral has the largest context window at 256,000 tokens, against 32,768 for Qwen Max. Maximum output per response: Codestral up to 4,096, Qwen Max up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Qwen Max accepts text. They handle the same number of input types.
Are any of these open source?
Codestral publishes its weights and can be self-hosted; Qwen Max is proprietary.
Which is newer?
Codestral is the newest, released May 29, 2024. Qwen Max came out Apr 3, 2024. Knowledge cutoff: Codestral Oct 2024, Qwen Max Apr 2024.
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.
