Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
- Codestral 2508Mistral AIRemove
- GPT-6 Astra ProOpenAIRemove
- DeepSeek V4.1 FlashDeepSeekRemove
- Hy4 previewTencentRemove
4 is the maximum. Remove one to add another.
| Attribute | Codestral 2508codestral-2508 | GPT-6 Astra Progpt-6-astra-pro | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Hy4 previewhy4-preview |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.45 / 1M | $10.00 / 1M | $0.30 / 1M | $0.834 / 1M |
| Output | $1.35 / 1M | $50.00 / 1M | $1.20 / 1M | $2.50 / 1M |
| Cache Write (5m) | $0.45 / 1M | $10.00 / 1M | $0.30 / 1M | $0.834 / 1M |
| Cache Write (1h) | $0.45 / 1M | $10.00 / 1M | $0.30 / 1M | $0.834 / 1M |
| Cache Read | $0.45 / 1M | $10.00 / 1M | $0.30 / 1M | $0.834 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 256K | 1M | 1M | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | Mistral AI | OpenAI | DeepSeek | Tencent |
| Category | chat | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — | — |
| Description | ||||
| Summary | Codestral is Mistral's cutting-edge language model for coding, released in late July 2025. It is purpose-built for low-latency, high-frequency developer workflows, excelling at tasks such as fill-in-the-middle (FIM) code completion, code correction, and test generation. Optimized for responsiveness and precision, Codestral is well suited for real-time coding assistance, IDE integration, and automated development pipelines where speed and accuracy are critical. | GPT-6 Astra Pro uses the same underlying model as GPT-6 Astra, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is well suited for demanding coding, analysis, and agentic workflows where solution quality takes priority over speed and cost. | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. | Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world workflows. |