StarSeaAPIStarSeaAPI
HomeCapabilitiesLong-context models

Long-context models

long context LLM API, 1M token context, large document analysis

Long context lets you skip a retrieval pipeline, but it does not make long context free: input tokens are billed whether they are cached or not, and a 200K-token prompt costs the same as the output of hundreds of normal requests. Repeated prefixes are the case where the platform's cache-aware routing pays off — keep the stable part of the prompt (system instructions, documents) at the front and the volatile part at the end, and repeated calls against the same prefix cost materially less.

Models (47)

ModelsProvidersInput $/MOutput $/MIntelligence indexCoding index
claude-opus-4-6Anthropic$5.00$25.00
claude-opus-4-7Anthropic$5.00$25.00
claude-opus-4-8Anthropic$5.00$25.00
claude-opus-5Anthropic$5.00$25.0054.178.0
claude-sonnet-4-6Anthropic$3.00$15.00
claude-sonnet-5Anthropic$2.00$10.0045.171.5
codex-auto-reviewOpenAI$2.50$15.00
deepseek-v4-flashDeepSeek$0.15$0.6140.869.1
deepseek-v4-flash-0731DeepSeek$0.15$0.61
deepseek-v4-proDeepSeek$0.68$2.0542.168.8
deepseek-v4-pro-0813DeepSeek$0.68$2.05
doubao-seed-2.0-liteByteDance Doubao$0.09$0.55
doubao-seed-2.0-miniByteDance Doubao$0.030$0.30
doubao-seed-2.1-turboByteDance Doubao$0.45$2.27
doubao-seed-evolvingByteDance Doubao$0.91$4.55
glm-4.6Zhipu AI$0.61$2.4245.8
glm-4.7Zhipu AI$0.30$1.2145.3
glm-5Zhipu AI$0.61$2.73
glm-5-turboZhipu AI$0.76$3.33
glm-5.1Zhipu AI$0.91$3.6455.8
glm-5.3Zhipu AI$1.21$4.2448.674.8
glm-5.3-flashZhipu AI$0.12$0.4246.271.5
gpt-5.5OpenAI$5.00$30.0074.9
gpt-5.6-solOpenAI$5.00$30.0051.377.4
gpt-5.6-terraOpenAI$2.00$12.0046.876.7
gpt-6-astraOpenAI$10.00$50.0054.776.9
grok-4.5xAI$2.00$6.0045.572.4
grok-4.6xAI$2.00$6.0050.676.8
hy3Tencent Hunyuan$0.15$0.61
k3Moonshot AI$3.03$15.15
kimi-k2.7-codeMoonshot AI$0.98$4.0960.8
kimi-k3Moonshot AI$3.03$15.1550.276.2
mimo-v2.5Xiaomi MiMo$0.15$0.3056.8
mimo-v2.5-proXiaomi MiMo$0.45$0.9132.660.2
MiniMax-M2MiniMax$0.32$1.27
MiniMax-M2.1MiniMax$0.32$1.27
MiniMax-M2.1-highspeedMiniMax$0.64$2.55
MiniMax-M2.5MiniMax$0.32$1.27
MiniMax-M2.5-highspeedMiniMax$0.64$2.55
MiniMax-M2.7MiniMax$0.32$1.2752.6
MiniMax-M2.7-highspeedMiniMax$0.64$2.55
minimax-m3MiniMax$0.64$2.5535.758.6
qwen3.6-flashAlibaba Qwen$0.18$1.09
qwen3.7-maxAlibaba Qwen$1.82$5.4566.0
qwen3.7-plusAlibaba Qwen$0.30$1.2155.9
qwen3.8-flashAlibaba Qwen$0.12$0.41
qwen3.8-maxAlibaba Qwen$1.82$5.4553.468.9

Prices are per 1M tokens in USD · ¥6.6 = $1

Capabilities

Chat & general-purpose models

56

Reasoning models

56

Coding models

54

Vision & multimodal input models

37

Image generation models

4

Low-cost models

19

Frontier models

12

OpenAI-compatible API

57