$5
No bonus
Top upPricing
Official price vs. our price, on every model.
25 frontier models from 8 providers behind one key — Anthropic, OpenAI, Google, DeepSeek, Doubao, GLM, Kimi, MiniMax. Claude as low as 82% off; DeepSeek · Doubao · GLM · Kimi at half price; OpenAI text & Gemini at list price. Priced in plain USD. Top up online or activate with a redeem code. Failures don't bill.
Discounts vs. official
Frontier models, well under list price.
We publish each provider's official list price next to ours — the tiers below are read live from the gateway rate card, so they always match what you're billed.
82% offAnthropic~82% below official list
55% offAnthropic~55% below official list
20% offOpenAI~20% below official list
List priceOpenAI · Google · DeepSeek · GLM · Kimi · MoreBilled at provider list rates
How to activate
Ways to get started today.
Top up online in the Console in seconds. Prefer another route? You can also:
Top up
Priced in plain US dollars.
Your balance never expires. Bonus tiers kick in automatically — the dollar amount you top up determines the bonus.
$50
Bonus +1.5%
≈ $50.75 effective
Top up$500
Bonus +5.0%
≈ $525 effective
Top up$1,250
Bonus +11.2%
≈ $1,390 effective
Top upYour balance never expires. Bonuses are applied at top-up time, not on spend. Failed requests don't bill — preview the cost via the x-bytespike-credits-estimated response header before the request runs.
Per-endpoint pricing
Official price vs. our price, per model.
Every provider's official list price next to ours, grouped by brand — discounts pulled live from the gateway's published rate card. Failures don't bill.
Anthropic
3| Model | Official | Our price | Discount |
|---|---|---|---|
| Claude Opus 5.5 Anthropic Claude Opus 5.5 (released 2026-09-22) — long-running agentic coding and knowledge work, native 1M context; adaptive thinking always on, default effort medium. | $4 / $20 | $0.72 / $3.6per 1M tokens | 82% off |
| Claude Sonnet 5.5 Anthropic Claude Sonnet 5.5 (released 2026-09-28) — the best combination of speed and intelligence, native 1M context; adaptive thinking on by default, default effort high. | $2 / $10 | $0.36 / $1.8per 1M tokens | 82% off |
| Claude Haiku 5.5 Anthropic Claude Haiku 5.5 (released 2026-10-07) — high-volume, latency-sensitive classification, extraction, routing and subagent work, native 1M context; adaptive thinking on by default, default effort medium; prompts over 100k tokens are billed at 5×. | $0.1 / $0.5 | $0.045 / $0.225per 1M tokens | 55% off |
OpenAI
5| Model | Official | Our price | Discount |
|---|---|---|---|
| GPT-6 Astra OpenAI's next-generation flagship (released 2026-09-03) — reasoning effort up to max. | $10 / $50 | $8 / $40per 1M tokens | 20% off |
| GPT-6 Luna OpenAI's most efficient GPT-6 model (released 2026-09-22) for focused, high-volume tasks — summarization, extraction, focused coding. | $0.1 / $0.5 | $0.08 / $0.4per 1M tokens | 20% off |
| GPT-6 Sol OpenAI's GPT-6 workhorse (released 2026-09-22) for complex coding and agentic workflows — reasoning effort none through max. | $2 / $10 | $1.6 / $8per 1M tokens | 20% off |
| GPT-6.1 Sol OpenAI's GPT-6.1 workhorse (released 2026-09-29) for coding and everyday work — reasoning effort low through max (none / minimal unsupported). | $2 / $10 | $1.6 / $8per 1M tokens | 20% off |
| GPT-6.1 Terra OpenAI's GPT-6.1 efficient tier (released 2026-10-26) for visual reasoning, precise computer use and clear, natural writing — reasoning effort none through max, default medium (minimal unsupported). | $1 / $5 | $1 / $5per 1M tokens | List price |
| Model | Official | Our price | Discount |
|---|---|---|---|
| Gemini 3.5 Flash Google's most intelligent model — sustained frontier performance, excels at agentic and coding tasks. | $1.5 / $9 | $1.5 / $9per 1M tokens | List price |
| Gemini 3.5 Transcribe Gemini speech-to-text on /v1/audio/transcriptions — automatic language detection, files up to 14MB. | $2 / $12 | $2 / $12per 1M tokens | List price |
| Gemini 3.8 Flash Lite TTS Lower-cost Gemini text-to-speech on /v1/audio/speech — 24kHz WAV output, Chinese supported. | $0.5 / $6 | $0.5 / $6per 1M tokens | List price |
| Gemini 3.8 Flash TTS Gemini text-to-speech on /v1/audio/speech — 24kHz WAV output, Chinese supported, 30 prebuilt voices. | $0.5 / $9 | $0.5 / $9per 1M tokens | List price |
| Gemini 3.8 Flash Always points to the newest Gemini Flash generation. | $0.75 / $3.75 | $0.75 / $3.75per 1M tokens | List price |
| Gemini 3.5 Flash Lite Always points to the newest Gemini Flash-Lite generation. | $0.3 / $2.5 | $0.3 / $2.5per 1M tokens | List price |
DeepSeek
2| Model | Official | Our price | Discount |
|---|---|---|---|
| DeepSeek V4.1 Flash DeepSeek V4.1 Flash — the vendor positions it as surpassing V4 Pro on quality, cost and speed. Accepts image input; deep thinking on by default and can be disabled. | $0.3 / $1.2 | $0.3 / $1.2per 1M tokens | List price |
| DeepSeek V4 Pro DeepSeek V4 Pro — significantly stronger agent capability and rich world knowledge; deep thinking on by default, can be disabled manually. | $1.32 / $3.96 | $1.32 / $3.96per 1M tokens | List price |
GLM
2| Model | Official | Our price | Discount |
|---|---|---|---|
| GLM 5.2 Zhipu's next-gen flagship model with native 1M-token context and adjustable thinking depth — excels at long-horizon coding and complex engineering optimization. | $1.179 / $4.127 | $1.179 / $4.127per 1M tokens | List price |
| GLM 5.3 Flash Zhipu's first native multimodal model in the GLM-5 series — 320B total / 18B active parameters, with image/video/file input and 1M-token context. | $0.15 / $0.5 | $0.15 / $0.5per 1M tokens | List price |
Kimi
2| Model | Official | Our price | Discount |
|---|---|---|---|
| Kimi K2.8 Preview (Code) Kimi Code K2.8 Preview (kimi-for-coding upgraded in place) — close to K3 with more efficient thinking; reasoning_effort low/high/max (default max), image+video, 1M context. | $0.95 / $4 | $0.95 / $4per 1M tokens | List price |
| Kimi K3 Kimi's flagship multimodal model (text/image/video input) with a 1M-token context window and always-on reasoning; Kimi Code defaults reasoning_effort to high. | $3 / $15 | $3 / $15per 1M tokens | List price |
More
5| Model | Official | Our price | Discount |
|---|---|---|---|
| Grok 4.7 xAI's current flagship for coding, agents, and knowledge work — 500k context, tunable reasoning_effort (default high, including xhigh). | $2 / $6 | $2 / $6per 1M tokens | List price |
| MiMo V2.6 Flash Xiaomi's cost-efficient multimodal MiMo model (309B total / 15B active) with a 1M-token context and tool calling; thinking is on by default and can be turned off. | $0.14 / $0.28 | $0.14 / $0.28per 1M tokens | List price |
| MiMo V2.6 Pro Xiaomi's flagship MiMo reasoning model with omni-modal input (text/image/video/audio), a 1M-token context and tool calling; thinking is on by default and can be turned off. | $0.435 / $0.87 | $0.435 / $0.87per 1M tokens | List price |
| Qwen3-VL Flash Alibaba's small Qwen3-VL vision-understanding model (text/image/video input) with a 256K-token context and tool calling; thinking is off by default and can be turned on. | $0.022 / $0.215 | $0.022 / $0.215per 1M tokens | List price |
| Qwen3.8 Flash Alibaba's Qwen3.8 Flash multimodal model (text/image/video input) with a 1M-token context and tool calling; thinking is on by default with adjustable effort and can be turned off. | $0.113 / $0.382 | $0.113 / $0.382per 1M tokens | List price |
Token prices are per 1M (input / output). Official is each provider's public list price; our price applies the family discount. Image models are billed per token; video is billed per clip. Failures don't bill — the final charge matches the estimated_credits returned at submit time.
rate card refreshed · 2026-10-28
Per-model rate card
25 models, transparent prices, refreshed live.
We publish official list price next to our price per million tokens for every chat model, and per-call rates for image and video. Sourced from the production gateway, refreshed once a day. No hidden tiers, no markup paragraphs.
Chat models
25
Image models
0
One key, one URL
llm.bytespike.ai/v1
All prices are quoted in U.S. dollars (USD). ByteSpike is pay-as-you-go: top up your balance, spend per the rate card — no plans, no minimums, no auto-renewal. Top up online at console.bytespike.ai/billing, or use a redeem code (console.bytespike.ai/billing#redeem). Your top-up balance never expires and failed requests don't bill. Stated prices exclude applicable taxes and VAT, calculated at activation based on your billing location.