Tokely
COMPARISONS

OpenAI API alternative with lower rates

Keep the OpenAI SDK and call GPT, Claude, Gemini, Kimi, DeepSeek and more at published per-model rates. Change the base URL and key; no platform fee.

Try in Playground Calculate your cost
By Tokely·Reviewed
THE SHORT ANSWER

Tokely is an OpenAI-compatible API: point the OpenAI SDK at https://api.tokely.me/v1, use a Tokely key, and call supported GPT models plus models from other developers from one balance. Many rates are below the developer's list price, and embeddings cost half of OpenAI's list price. Batch and Assistants are not offered.

Compare a matched text workload

USD per 1M tokens. Example: 1M uncached input + 250K output. Tokely rates dated 2026-10-12; model developer references checked 2026-10-05. Platform/checkout fees, taxes, special units and context tiers excluded. Different models are not quality equivalents. Methodology.
ModelTokely input / outputTokely examplemodel developer exampleDiscount vs model developer
GPT-5.4 MiniOpenAI$0.3 / $1.8Cache read: $0.03$0.75$1.875$0.75 / $4.5 per 1M60.0% off
Claude Haiku 5.5Anthropic$0.042353 / $0.211764Cache read: $0.042353$0.095294$0.225$0.1 / $0.5 per 1M57.6% off
GPT-5 NanoOpenAI$0.035 / $0.28Cache read: $0.0035$0.105$0.15$0.05 / $0.4 per 1M30.0% off
Gemini 2.5 Flash LiteGoogle$0.07 / $0.28Cache read: $0.007$0.14$0.2$0.1 / $0.4 per 1M30.0% off
GPT-4.1 NanoOpenAI$0.07 / $0.28Cache read: $0.0175$0.14$0.2$0.1 / $0.4 per 1M30.0% off
GPT-6 LunaOpenAI$0.07 / $0.35Cache read: $0.007$0.1575$0.225$0.1 / $0.5 per 1M30.0% off
GPT-4o MiniOpenAI$0.105 / $0.42Cache read: $0.0525$0.21$0.3$0.15 / $0.6 per 1M30.0% off
GPT-OSS 120BOpenAI$0.1331 / $0.5324Cache read: $0.1331$0.2662Not matched—
Grok 4.3Grok$0.1875 / $0.375Cache read: $0.1875$0.28125$1.875$1.25 / $2.5 per 1M85.0% off
Gemini Embedding 001Google$0.158825 / $0.635299Cache read: $0.158825$0.31765Not matched—
GPT-5.6 LunaOpenAI$0.14 / $0.84Cache read: $0.014$0.35$0.5$0.2 / $1.2 per 1M30.0% off
MiMo V2.6 FlashXiaomi$0.252 / $0.504Cache read: $0.252$0.378Not matched—
GLM 5.3 FlashChatGLM$0.20625 / $0.6875Cache read: $0.04125$0.378125$0.275$0.15 / $0.5 per 1M37.5% higher
DeepSeek V4.1 FlashDeepSeek$0.2 / $0.8Cache read: $0.004$0.4$0.3$0.15 / $0.6 per 1M33.3% higher
Gemini 3.1 Flash LiteGoogle$0.175 / $1.05Cache read: $0.0175$0.4375$0.625$0.25 / $1.5 per 1M30.0% off
GPT-5 MiniOpenAI$0.175 / $1.4Cache read: $0.0175$0.525$0.75$0.25 / $2 per 1M30.0% off
GPT-5.1 Codex MiniOpenAI$0.175 / $1.4Cache read: $0.0175$0.525$0.75$0.25 / $2 per 1M30.0% off
GLM 4.5 AirChatGLM$0.2475 / $1.210007Cache read: $0$0.550002$0.475$0.2 / $1.1 per 1M15.8% higher
Qwen 3.8 FlashQwen$0.309375 / $0.969375Cache read: $0.033011$0.551719$0.2085$0.113 / $0.382 per 1M164.6% higher
GPT-4.1 MiniOpenAI$0.28 / $1.12Cache read: $0.07$0.56$0.8$0.4 / $1.6 per 1M30.0% off
Grok Build 0.1Grok$0.404415 / $0.80883Cache read: $0.404415$0.606623$1.5$1 / $2 per 1M59.6% off
GPT-5.4 NanoOpenAI$0.242 / $1.5125Cache read: $0.242$0.620125$0.5125$0.2 / $1.25 per 1M21.0% higher
Llama 3.2 1B InstructMeta$0.6 / $0.15Cache read: $0.6$0.6375Not matched—
Gemini 2.5 FlashGoogle$0.21 / $1.75Cache read: $0.021$0.6475$0.925$0.3 / $2.5 per 1M30.0% off
Gemini 3.5 Flash LiteGoogle$0.21 / $1.75Cache read: $0.021$0.6475$0.925$0.3 / $2.5 per 1M30.0% off
Grok 4.20 Non ReasoningGrok$0.505519 / $1.011038Cache read: $0.505519$0.758279$1.875$1.25 / $2.5 per 1M59.6% off
Grok 4.20 ReasoningGrok$0.505519 / $1.011038Cache read: $0.505519$0.758279$1.875$1.25 / $2.5 per 1M59.6% off
MiMo V2.6 ProXiaomi$0.522 / $1.044Cache read: $0.522$0.783Not matched—
DeepSeek V3.1DeepSeek$0.478335 / $1.435005Cache read: $0.478335$0.837086Not matched—
Gemini 3 Flash PreviewGoogle$0.35 / $2.1Cache read: $0.035$0.875$1.25$0.5 / $3 per 1M30.0% off
GPT-3.5 TurboOpenAI$0.528 / $1.584Cache read: $0.528$0.924$0.875$0.5 / $1.5 per 1M5.6% higher
MiniMax M2.5MiniMax$0.515625 / $1.65Cache read: $0.4125$0.928125$0.6$0.3 / $1.2 per 1M54.7% higher
Qwen 3.5 35B A3BQwen$0.33 / $2.64Cache read: $0.234667$0.99$0.75$0.25 / $2 per 1M32.0% higher
DeepSeek V4 FlashDeepSeek$0.605 / $1.815Cache read: $0.01925$1.05875Not matched—
Gemini 3.7 FlashGoogle$0.525 / $2.625Cache read: $0.0525$1.18125$1.6875$0.75 / $3.75 per 1M30.0% off
Gemini 3.8 FlashGoogle$0.525 / $2.625Cache read: $0.0525$1.18125$1.6875$0.75 / $3.75 per 1M30.0% off
Gemini 3.6 FlashGoogle$0.525 / $2.625Cache read: $0.0525$1.18125$1.6875$0.75 / $3.75 per 1M30.0% off
Qwen 3.6 35B A3BQwen$0.5 / $3Cache read: $0.333333$1.25$0.9375$0.375 / $2.25 per 1M33.3% higher
Llama 3.2 3B InstructMeta$1.2 / $0.6Cache read: $1.2$1.35Not matched—
o3 MiniOpenAI$0.77 / $3.08Cache read: $0.385$1.54$2.2$1.1 / $4.4 per 1M30.0% off
o4 MiniOpenAI$0.77 / $3.08Cache read: $0.1925$1.54$2.2$1.1 / $4.4 per 1M30.0% off
Qwen 3.5 122B A10BQwen$0.53 / $4.24Cache read: $0.765556$1.59$1.2$0.4 / $3.2 per 1M32.5% higher
Llama 3.3 70B InstructMeta$1.296 / $1.296Cache read: $1.296$1.62Not matched—
GLM 4.5ChatGLM$0.825 / $3.3Cache read: $0.825$1.65$1.15$0.6 / $2.2 per 1M43.5% higher
MiniMax M3MiniMax$0.825 / $3.3Cache read: $0.165$1.65$0.6$0.3 / $1.2 per 1M175.0% higher
GPT-6.1 SolOpenAI$0.8 / $4Cache read: $0.04$1.8$4.5$2 / $10 per 1M60.0% off
MiniMax M2.7MiniMax$0.9075 / $3.63Cache read: $0.9075$1.815$0.6$0.3 / $1.2 per 1M202.5% higher
Kimi K2.5Moonshot$0.825 / $4.33125Cache read: $0.825$1.907813Not matched—
Qwen 3 235B A22BQwen$0.9625 / $3.85Cache read: $0$1.925Not matched—
Doubao Seed 2.1 ProDoubao$0.89 / $4.45Cache read: $0.89$2.0025Not matched—
Grok 4.5Grok$1.4 / $4.2Cache read: $0.21$2.45$3.5$2 / $6 per 1M30.0% off
Grok 4.6Grok$1.4 / $4.2Cache read: $0.35$2.45$3.5$2 / $6 per 1M30.0% off
Grok 4.7Grok$1.4 / $4.2Cache read: $0.35$2.45$3.5$2 / $6 per 1M30.0% off
Gemini 2.5 ProGoogle$0.875 / $7Cache read: $0.0875$2.625$3.75$1.25 / $10 per 1M30.0% off
Gemini 3.5 FlashGoogle$1.05 / $6.3Cache read: $0.105$2.625$3.75$1.5 / $9 per 1M30.0% off
GPT-5 CodexOpenAI$0.875 / $7Cache read: $0.0875$2.625$3.75$1.25 / $10 per 1M30.0% off
GPT-5.1 CodexOpenAI$0.875 / $7Cache read: $0.0875$2.625$3.75$1.25 / $10 per 1M30.0% off
GPT-5OpenAI$0.875 / $7Cache read: $0.0875$2.625$3.75$1.25 / $10 per 1M30.0% off
GPT-5.1OpenAI$0.875 / $7Cache read: $0.0875$2.625$3.75$1.25 / $10 per 1M30.0% off
Kimi K2.6Moonshot$1.30625 / $5.426025Cache read: $0.221058$2.662756$1.95$0.95 / $4 per 1M36.6% higher
Kimi K2.7 CodeMoonshot$1.30625 / $5.426025Cache read: $0.26125$2.662756$1.95$0.95 / $4 per 1M36.6% higher
Qwen 3.8 MaxQwen$1.5345 / $4.60443Cache read: $0.3$2.685608$2.88775$1.65 / $4.951 per 1M7.0% off
GPT-4.1OpenAI$1.4 / $5.6Cache read: $0.35$2.8$4$2 / $8 per 1M30.0% off
o3OpenAI$1.4 / $5.6Cache read: $0.35$2.8$4$2 / $8 per 1M30.0% off
Llama 3.1 8BMeta$2.4 / $2.4Cache read: $2.4$3Not matched—
Qwen 3.6 27BQwen$1.2375 / $7.425Cache read: $1.2375$3.09375$1.5$0.6 / $3.6 per 1M106.3% higher
GPT-6 SolOpenAI$1.4 / $7Cache read: $0.14$3.15$4.5$2 / $10 per 1M30.0% off
Gemini 4 ArgonGoogle$1.4 / $7Cache read: $0.07$3.15$4.5$2 / $10 per 1M30.0% off
DeepSeek V4 ProDeepSeek$1.815 / $5.445Cache read: $0.060494$3.17625Not matched—
GLM 5.3ChatGLM$1.85 / $5.81Cache read: $0.4588$3.3025$2.5$1.4 / $4.4 per 1M32.1% higher
HY4 PreviewTencent$1.90152 / $5.70228Cache read: $1.90152$3.32709$1.45925$0.834 / $2.501 per 1M128.0% higher
Claude Sonnet 5Anthropic$1.5 / $7.5Cache read: $0.15$3.375$4.5$2 / $10 per 1M25.0% off
Claude Sonnet 5.5Anthropic$1.5 / $7.5Cache read: $0.075$3.375$4.5$2 / $10 per 1M25.0% off
GPT-Chat LatestOpenAI$1.375 / $8.25Cache read: $1.375$3.4375Not matched—
GLM 5.2ChatGLM$1.925 / $6.050001Cache read: $0.48125$3.4375$2.5$1.4 / $4.4 per 1M37.5% higher
GPT-5.6 TerraOpenAI$1.4 / $8.4Cache read: $0.14$3.5$5$2 / $12 per 1M30.0% off
Gemini 3.1 Pro PreviewGoogle$1.4 / $8.4Cache read: $0.14$3.5$5$2 / $12 per 1M30.0% off
GPT-4oOpenAI$1.75 / $7Cache read: $0.875$3.5$5$2.5 / $10 per 1M30.0% off
GPT-5.2OpenAI$1.225 / $9.8Cache read: $0.1225$3.675$5.25$1.75 / $14 per 1M30.0% off
GPT-5.2 CodexOpenAI$1.225 / $9.8Cache read: $0.1225$3.675$5.25$1.75 / $14 per 1M30.0% off
GPT-5.3 CodexOpenAI$1.225 / $9.8Cache read: $0.1225$3.675$5.25$1.75 / $14 per 1M30.0% off
Qwen 3.5 27BQwen$1.2375 / $9.9Cache read: $0$3.7125$0.9$0.3 / $2.4 per 1M312.5% higher
Qwen 3.8 27BQwen$1.5125 / $9.075Cache read: $0.3025$3.78125$0.848$0.424 / $1.696 per 1M345.9% higher
GLM 5ChatGLM$2.0625 / $7.425Cache read: $0$3.91875$1.8$1 / $3.2 per 1M117.7% higher
GPT-5.4OpenAI$1.75 / $10.5Cache read: $0.175$4.375$6.25$2.5 / $15 per 1M30.0% off
Qwen 3.7 PlusQwen$2.475 / $9.9Cache read: $0.495$4.95$0.8$0.4 / $1.6 per 1M518.8% higher
GPT-5.5OpenAI$2 / $12Cache read: $0.2$5$12.5$5 / $30 per 1M60.0% off
Claude Sonnet 4.6Anthropic$2.25 / $11.25Cache read: $0.225$5.0625$6.75$3 / $15 per 1M25.0% off
Qwen 3.5 397B A17BQwen$2.0625 / $12.375Cache read: $0$5.15625$1.5$0.6 / $3.6 per 1M243.8% higher
Qwen 3.7 MaxQwen$3.4375 / $10.3125Cache read: $0.6875$6.015625$2.88775$1.65 / $4.951 per 1M108.3% higher
Kimi K3Moonshot$2.7 / $13.5Cache read: $0.27$6.075$6.75$3 / $15 per 1M10.0% off
GPT-5.6 SolOpenAI$2.8 / $14Cache read: $0.28$6.3$9$4 / $20 per 1M30.0% off
GLM 5.1ChatGLM$3.85 / $10.587504Cache read: $0.977308$6.496876$2.5$1.4 / $4.4 per 1M159.9% higher
Claude Opus 5.5Anthropic$3 / $15Cache read: $0.15$6.75$9$4 / $20 per 1M25.0% off
Qwen 3.5 PlusQwen$2.75 / $16.5Cache read: $0$6.875$1$0.4 / $2.4 per 1M587.5% higher
Llama 3.1 70BMeta$4.8 / $9.6Cache read: $4.8$7.2Not matched—
Qwen PlusQwen$1.98 / $23.76Cache read: $0$7.92$0.7$0.4 / $1.2 per 1M1031.4% higher
Claude Opus 4.6Anthropic$3.75 / $18.75Cache read: $0.375$8.4375$11.25$5 / $25 per 1M25.0% off
Claude Opus 4.7Anthropic$3.75 / $18.75Cache read: $0.375$8.4375$11.25$5 / $25 per 1M25.0% off
Claude Opus 4.8Anthropic$3.75 / $18.75Cache read: $0.375$8.4375$11.25$5 / $25 per 1M25.0% off
Claude Opus 5Anthropic$3.75 / $18.75Cache read: $0.375$8.4375$11.25$5 / $25 per 1M25.0% off
Claude Opus 4.5Anthropic$3.75 / $18.75Cache read: $0.375$8.4375$11.25$5 / $25 per 1M25.0% off
GPT-6 AstraOpenAI$4 / $20Cache read: $0.4$9$22.5$10 / $50 per 1M60.0% off
Qwen 3.6 PlusQwen$4.125 / $24.75Cache read: $0$10.3125$1.25$0.5 / $3 per 1M725.0% higher
GPT-4 TurboOpenAI$7 / $21Cache read: $4.4$12.25$17.5$10 / $30 per 1M30.0% off
Claude Fable 5Anthropic$7.5 / $37.5Cache read: $0.75$16.875$22.5$10 / $50 per 1M25.0% off
Claude Fable 5.1Anthropic$7.5 / $37.5Cache read: $0.1875$16.875$22.5$10 / $50 per 1M25.0% off
o1OpenAI$10.5 / $42Cache read: $5.25$21$30$15 / $60 per 1M30.0% off
o3 ProOpenAI$14 / $56Cache read: $8.8$28$40$20 / $80 per 1M30.0% off
GPT-4OpenAI$21 / $42Cache read: $6.6$31.5$45$30 / $60 per 1M30.0% off
GPT-5 ProOpenAI$10.5 / $84Cache read: $6.6$31.5$45$15 / $120 per 1M30.0% off
GPT-5.2 ProOpenAI$14.7 / $117.6Cache read: $21$44.1$63$21 / $168 per 1M30.0% off
GPT-5.4 ProOpenAI$21 / $126Cache read: $13.2$52.5$75$30 / $180 per 1M30.0% off
GPT-5.5 ProOpenAI$121.3245 / $545.96025Cache read: $0$257.814563$75$30 / $180 per 1M243.8% higher

Change the token mix in the calculator →

Same SDK, more models

Chat Completions and a stateless Responses subset follow the OpenAI shape for supported models. The same client can call Claude, Gemini, Grok, Kimi, DeepSeek and others by changing the model ID.

Compare the exact model

The table lists enabled text models with the developer's published price and the Tokely rate. Compare the same model and your own token mix in the calculator; a different model is a separate quality decision.

What does not move over

Batch API, Assistants, uploaded file IDs, fine-tuning and realtime audio are not offered. Keep those on OpenAI if you depend on them and move the chat traffic.

One key for every model

Every model on this page is available through one OpenAI-compatible endpoint and one balance, with routing modes, bounded fallback, spending limits and request logs.

LLM gateway: one API for every model ↗

A hosted LLM gateway with one OpenAI-compatible endpoint, account routing modes, bounded fallback, spending limits and request logs. Text, image, video and audio from one balance.

OpenAI-compatible API for Claude, Gemini, GPT and more ↗

Keep the OpenAI SDK and call Claude, Gemini, GPT, Kimi, GLM and other supported models. Change the base URL, key and model ID.

Questions before you switch

Is Tokely cheaper than the OpenAI API?

For many models, yes: see the per-model table. It is not cheaper for every model or request.

Do I need to change my code?

Usually only the base URL, API key and model ID. Check the model page for endpoint and parameter support.

KEEP EXPLORING

More on comparisons

All 61 resources
FROM THE BLOG

Read next

All articles
START WITH YOUR OWN WORKLOAD

Know the price.
Then make the call.

Check the model, compare the rate, and connect with a Tokely key.

Explore models Read the quickstart