DeepSeek
DeepSeek is tracked from the official English API docs. The current line lists deepseek-v4-flash and deepseek-v4-pro with 1M context, 384K maximum output, thinking/non-thinking modes, JSON output, tool calls, context caching and OpenAI/Anthropic-compatible endpoints. V4-Flash costs $0.0028/M cache-hit input, $0.14/M cache-miss input and $0.28/M output; V4-Pro costs $0.003625, $0.435 and $0.87 respectively. The former deepseek-chat and deepseek-reasoner compatibility aliases are no longer listed on the current pricing page after their July 24 deprecation date.
Editorial verdict
Developers evaluating Chinese model APIs for coding agents, reasoning, tool use and OpenAI/Anthropic-compatible migration.
Avoid new integrations that still hard-code deepseek-chat or deepseek-reasoner without a migration plan to V4 model names.
The English docs now make DeepSeek's current API shape explicit: V4-Pro/V4-Flash, dual OpenAI/Anthropic compatibility, thinking mode, tool calls, caching and agent-tool integrations.
V4-Flash from $0.0028/M cache-hit input, $0.14/M cache-miss input and $0.28/M output tokens
Topped-up balance, Granted balance, Platform billing
API commercial use should follow the active platform terms.
Treat prompts and logs as vendor-processed data unless enterprise terms say otherwise.
Use deepseek-v4-pro or deepseek-v4-flash directly rather than relying on retired compatibility aliases.
Official docs list integrations for Claude Code, GitHub Copilot, OpenCode, Kilo Code, OpenClaw and other agent tools.
V4 models document 1M context, 384K max output and context caching with cache-hit usage fields.
Pricing was rechecked on August 4, 2026. The current page lists V4-Flash and V4-Pro, no longer lists the legacy aliases, and says peak/off-peak pricing will be introduced on a date to be announced.
Qwen is one option when deployment and cloud billing matter.
Kimi API is a cataloged reference for English documentation, token billing and agent-oriented models.
docs · en · verified 2026-05-17
Confirms English docs, OpenAI/Anthropic compatibility, V4 model names and legacy alias deprecation date.
pricing · en · verified 2026-08-04
Lists V4-Pro and V4-Flash with 1M context, 384K maximum output, features, cache-hit/cache-miss/output prices, 2,500/500 concurrency limits and the forthcoming peak/off-peak pricing policy.
docs · en · verified 2026-05-17
Confirms Claude Code and agent-tool integration paths through the Anthropic-compatible endpoint.
docs · en · verified 2026-05-17
Confirms the 2026-04-24 DeepSeek-V4 update and alias deprecation schedule.
Last checked: 2026-08-04