Codestral 25.08 vs GLM-4.5-Air vs Claude Haiku 4.5
Too close to call on our weighted score (GLM-4.5-Air 48, Claude Haiku 4.5 47, Codestral 25.08 47). The right pick depends on what you value most.
Mistral AICodestral 25.08
47/100- ECI—
- Price$0.30 / $0.90
- Context128K
Z.ai (Zhipu)GLM-4.5-Air
48/100- ECI—
- Price$0.20 / $1.10
- Context131K
AnthropicClaude Haiku 4.5
47/100- ECI142.2
- Price$1.00 / $5.00
- Context200K
Too close to call
It is close. Our weighted score puts them within a point (GLM-4.5-Air 48/100, Claude Haiku 4.5 47/100, Codestral 25.08 47/100), so choose by what matters most for your work: GLM-4.5-Air on price and Claude Haiku 4.5 for long inputs. 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 priceGLM-4.5-AirGLM-4.5-Air $0.425 · Codestral 25.08 $0.45 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 4.5Claude Haiku 4.5 200,000 · GLM-4.5-Air 131,072 · Codestral 25.08 128,000 tokens
- Widest inputsClaude Haiku 4.5Codestral 25.08: Text · GLM-4.5-Air: Text · Claude Haiku 4.5: Text, Images, PDFs
- Self-hostingGLM-4.5-AirPublishes downloadable weights
| Measure | Weight | Codestral 25.08 | GLM-4.5-Air | Claude Haiku 4.5 |
|---|---|---|---|---|
| Price | 50% | 64 | 65 | 34 |
| Inputs & features | 30% | 35 | 35 | 80 |
| Context window | 20% | 24 | 25 | 32 |
| Overall | 100% | 47/100 | 48/100 | 47/100 |
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 | Codestral 25.08Mistral AI | GLM-4.5-AirZ.ai (Zhipu) | Claude Haiku 4.5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | 142.2 |
| ECI rank | — | — | #102 of 165 |
| GPQA DiamondGraduate-level science questions | — | — | 71.2% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 66.7% |
| SimpleQA VerifiedShort factual questions | — | — | 13.2% |
| Price per million tokens | |||
| Input | $0.30 | $0.20 (best) | $1.00 |
| Output | $0.90 (best) | $1.10 | $5.00 |
| Cached input | $0.03 (best) | $0.03 (best) | $0.10 |
| Blended (3:1) | $0.45 | $0.425 (best) | $2.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Z.AI API | Official Anthropic API |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens | 200,000 tokens (best) |
| Max output | 8,192 tokens | 98,304 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | codestral-2508 | glm-4.5-air | claude-haiku-4-5 |
| API providers | 11 | 19 | 48 (best) |
| Released | Jul 30, 2025 | Jul 28, 2025 | Oct 15, 2025 |
| Knowledge cutoff | — | Apr 2025 | Feb 28, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral 25.08$4.80
- GLM-4.5-Air$4.20
- Claude Haiku 4.5$20.00
Which should you choose?
Which is better: Codestral 25.08, GLM-4.5-Air or Claude Haiku 4.5?
It is close. Our weighted score puts them within a point (GLM-4.5-Air 48/100, Claude Haiku 4.5 47/100, Codestral 25.08 47/100), so choose by what matters most for your work: GLM-4.5-Air on price and Claude Haiku 4.5 for long inputs. 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 25.08, GLM-4.5-Air or Claude Haiku 4.5?
GLM-4.5-Air is cheaper at $0.20 input / $1.10 output per million tokens (official Z.AI API price). Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.425 per million tokens for GLM-4.5-Air versus $0.45 for Codestral 25.08 (1.1× as much) and $2.00 for Claude Haiku 4.5 (4.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, GLM-4.5-Air has not been scored yet and Claude Haiku 4.5 has an ECI of 142.2.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral 25.08, GLM-4.5-Air and Claude Haiku 4.5 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?
Claude Haiku 4.5 has the largest context window at 200,000 tokens, against 131,072 for GLM-4.5-Air and 128,000 for Codestral 25.08. Maximum output per response: Codestral 25.08 up to 8,192, GLM-4.5-Air up to 98,304, Claude Haiku 4.5 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
Codestral 25.08 accepts text; GLM-4.5-Air accepts text; Claude Haiku 4.5 accepts text, images and PDFs. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
GLM-4.5-Air publishes its weights and can be self-hosted; Codestral 25.08 and Claude Haiku 4.5 is proprietary.
Which is newer?
Claude Haiku 4.5 is the newest, released Oct 15, 2025. Codestral 25.08 came out Jul 30, 2025; GLM-4.5-Air came out Jul 28, 2025. Knowledge cutoff: GLM-4.5-Air Apr 2025, Claude Haiku 4.5 Feb 28, 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 Nov 2, 2026.
Related comparisons
- Codestral 25.08 vs Llama 3.3 Nemotron Super 49B v1.5NVIDIA
- Codestral 25.08 vs ERNIE 4.5 300B A47BBaidu
- Codestral 25.08 vs Qwen3 Omni 30B A3B ThinkingAlibaba (Qwen)
- GLM-4.5-Air vs Llama 3.3 Nemotron Super 49B v1.5NVIDIA
- GLM-4.5-Air vs Qwen3 Omni 30B A3B ThinkingAlibaba (Qwen)
- GLM-4.5-Air vs ERNIE 4.5 300B A47BBaidu
