Text plus multimodal aggregation, transparent credits, enterprise-ready — one Anthropic-compatible Gateway for every frontier model you actually use.
curl https://llm.bytespike.ai/v1/chat/completions \
-H "Authorization: Bearer $BS_KEY" \
-d '{"model":"claude-sonnet-4-6","messages":[{"role":"user","content":"Hi"}]}'One gateway · 36 frontier models
See all →24 endpoints, one key
Image, video, text, account, async jobs — the full catalog. Each card links to the endpoint reference; bring your own integration.
1024² · text-to-image
ByteDance's flagship aesthetic image generator. Strong on illustration, packaging, and editorial stills with native CJK prompt understanding.
2048² · refined edges
Refined V4 with sharper edges and tighter prompt adherence; the daily-driver upgrade.
1024² · low-latency
Latency-tuned variant for product cards, thumbnails, and mass A/B image testing.
1024² · prompt-faithful
OpenAI's image generation endpoint. Highest prompt fidelity, strong typography handling, photorealistic outputs.
768² · sketch-to-image
Sketch-grounded image generation. Stable across iterations — pair with a quick layout pass for storyboards.
1024² · stylized
Style-leaning V2 — better at illustrative, anime, and editorial-stylized output than the base model.
Pricing is per call. Credits are released on failure. estimated_credits is returned at submit time so you can show users the cost before they confirm.
Why ByteSpike
Aggregated volume pricing plus failed-call refunds. Most teams cut their AI infra bill by 20-40% the first month.
24 endpoints across image / video / text / async jobs / account — every frontier model worth shipping against, behind one Anthropic-shape API.
Switch base_url, paste your key, ship. OpenAI Chat Completions and Anthropic Messages both drop in unchanged.
Lisahost LA backbone + Cloudflare edge. Median gateway overhead under 80ms. tool_use, cache_control, thinking pass through transparently.
DOSIA pairs natively. Free credits on signup. No card. estimated_credits returned at submit time so you show users the cost before they confirm.
Self-hosted SKU, SSO/OIDC, audit log, org-level wallets, per-key quota / rate limit / IP allowlist controls. Talk to sales when you're ready.
Curated starting points
ByteSpike ships with two curated model packs so you don't pick from 30 SKUs on day one. Apply Global or China with one click; refine per team once you know which models earn their keep.
For international or English-first workloads.
Claude · GPT-5 · Gemini · DeepSeek V4
For PRC compliance or PII-sensitive workloads.
DeepSeek · Doubao · GLM · Kimi · MiniMax
Custom templates layer on top — fork a preset, swap in DeepSeek Flash, drop image gen, save as your team's stack. Per-member overrides intersect with the team allow-list server-side.
How org admins use presetsModel catalog
36 models across chat, image, and video — behind a single Anthropic-shape API.
Claude Opus 4.8
anthropicLatest Opus flagship. Codebase-scale reasoning.
Claude Sonnet 4.6
anthropicProduction mid-tier. 5× cheaper than Opus.
Claude Haiku 4.5
anthropicFast + cheap. High-volume classification.
DeepSeek V3 (Anthropic)
deepseekV3.2 via Anthropic Messages. Keep your SDK.
DeepSeek V3.2
deepseekStandard DeepSeek chat. OpenAI-shape.
DeepSeek V4 Flash
deepseekV4 fast tier. Latency-optimized.
DeepSeek V4 Pro
deepseekV4 flagship. Broader reasoning.
DeepSeek R1
deepseekExplicit reasoning chain. Math + code.
GPT-5.5
openaiCurrent OpenAI flagship. Vision + reasoning.
GPT-5.4
openaiGPT-5 workhorse. Reasoning mid-tier.
GPT-5.4 Mini
openaiCheap GPT-5. Cost-sensitive chat.
GPT-5.4 Nano
openaiCheapest GPT-5. High-volume tasks.
GPT-5.2
openaiGPT-5 base tier. Reliable general chat.
Gemini 3.1 Pro
googleGoogle flagship. Vision on image + video.
Gemini 3.5 Flash
googleLatest Flash. Fast vision at 1M context.
Gemini 3 Flash
googleFast Google tier. Cheap vision.
Gemini 2.5 Flash
googleFast Google tier. Cost-sensitive vision.
Doubao Seed 2.0 Pro
doubaoByteDance chat flagship. Strong Chinese reasoning.
GLM-5.1
glmZhipu AI flagship. Chinese reasoning.
Kimi K2.6
kimiMoonshot AI. Long-context Chinese.
MiniMax M2.7
minimaxMiniMax chat model. Cost-effective.
GPT Image 2
openaiOpenAI flagship. Typography + layout fidelity.
Nano Banana
googleGoogle lightweight. Volume-friendly.
Nano Banana v2
googleAdds image-to-image. Same cost as v1.
Seedream 4
doubaoByteDance flagship. Chinese poster + aesthetic.
Seedream 4.5
doubaoRefined 4. Tighter prompt adherence.
Seedream V5 Lite
doubaoCheapest image tier. Programmatic volume.
Sora 2
openaiOpenAI flagship video. Physics + motion.
Sora 2 Pro
openaiUp to 30s clips. Subject persistence.
Veo 3.1
googleGoogle flagship. Native audio generation.
Veo 3.1 Fast
googleCheaper Veo. No audio, faster runtime.
Seedance 1.5 Pro
doubaoPrevious Seedance flagship. Compat reference.
Seedance Pro
doubaoByteDance video flagship. Chinese aesthetic.
Seedance Pro Fast
doubaoSame Pro weights, faster runtime.
Seedance 2
doubaoNext-gen Seedance. Higher fidelity motion.
Seedance 2 Fast
doubaoCheapest Seedance 2. Volume video.
Companion app
The macOS desktop AI companion that pairs natively with your ByteSpike account. Lark bridge, browser automation, fifty-plus skills — one login, no extra config.
ByteSpike powers the API · DOSIA delivers the experience · One account, everywhere.
Last 24 hours
No PRs shipped in the last 24 hours
Feed generated:
From the blog
ByteSpike ships with two curated model presets — Global and China — and every account opens to one of them already applied. We get asked why we didn't just let admins pick from 30 models on day one. Here's the rationale.
You shouldn't have to keep three apps open to get a marketing kit done. DOSIA's main brain now picks up image generation, image analysis, video, and 'use a different LLM' as native capabilities — one OAuth connect to ByteSpike, then you just type what you want.
Every ByteSpike call carries a pre-flight credit reservation and a settle-on-success commit. Reservations expire if the upstream errors out, the user cancels, or the gateway times out — the account ledger only debits when there's an asset or a token stream that landed.
Early customer cohort
ByteSpike just opened to public preview. The first 50 teams who integrate get a direct line to the engineering team, retroactive credit on any pricing change, and their logo featured here once they're ready to be quoted publicly.
hello@bytespike.ai · response within 1 business day
FAQ
Pair DOSIA with your account in two minutes — or talk to sales for a private deployment.