A model that completes a 20-line function is not the same product as a model that reads half a monorepo and calls tools. Output is expensive, tool calls fail in boring ways, and long context burns money. Use this page to pick a primary coding model and a cheaper fallback, then decide budget rules before agents run unsupervised.
來源依據: NextModel use-case taxonomy and OpenRouter supported-parameter metadata when available. · 更新日期 2026-07-01
如何使用这份名单
匹配分
先從候選名單開始，再以真實提示詞測試，並在接入正式環境路由前比較月度成本。
DeepSeek-V4-1-Flash-GLB via NextModel: 1M-token context; $0.3 / 1M tokens in / $1.20 / 1M tokens out per 1M tokens. Capabilities: streaming.
Whisper Large V3 Turbo via NextModel: context unpublished; $0 / 1M tokens in / $0 / 1M tokens out per 1M tokens. Capabilities: streaming.
Gemini 4 Argon via NextModel: 1M-token context; $2 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Claude Haiku 5.5 via NextModel: 1M-token context; Starting at $0.1 / 1M tokens in / $0.5 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
比較表
當你在縮小正式環境候選名單、建立備援策略或比較模型經濟性時，可使用此視圖。
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-V4-1-Flash-GLBdeepseek/deepseek-v4-1-flash-glb | DeepSeek | $0.3 / 1M tokens | $1.20 / 1M tokens | 1M | Streaming | Chinese Q&A, general chat | 1557-3097ms | Catalog | Platform curated |
| Whisper Large V3 Turboopenai/whisper-large-v3-turbo | OpenAI | $0 / 1M tokens | $0 / 1M tokens | — | Streaming | General chat via OpenAI, API workloads | 0-0ms | Catalog | Platform curated |
| Gemini 4 Argongoogle/gemini-4-argon | $2 / 1M tokens | $10 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 2974-10589ms | Catalog | Platform curated | |
| Claude Haiku 5.5anthropic/claude-haiku-5.5 | Anthropic | Starting at $0.1 / 1M tokens | $0.5 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1321-2017ms | Catalog | Platform curated |
| Doubao Seedance 2.5doubao/doubao-seedance-2-5-260628 | Doubao | $0.225 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Dreamina-Seedance 2.0 Fastdreamina/dreamina-seedance-2-0-fast-260128 | Dreamina | $0.122 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Dreamina Seedance 2.5dreamina/dreamina-seedance-2-5-260628 | Dreamina | $0.234 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Gemini 3 Pro Image (Nano Banana Pro) gemini/gemini-3-pro-image | Gemini | $0.314 / image | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
常見問題
Reliable tool calling, structured output, enough context for the repo slice you send, and instructions it actually follows. Token price alone is a poor proxy.
Cap budgets per project, watch output tokens, and send simple tasks to cheaper models. Escalate only when quality checks fail.
相关排行榜