YepAPI

Command Palette

Search for a command to run...

NEW MODELSeptember 27, 2026·New Model

48 new LLM models — GPT-6, Claude Fable 5.1 & Opus 5.5, Gemini 3.8 Flash, Grok 4.7 and more

Every current-generation model from OpenAI, Anthropic, Google, xAI, Meta, DeepSeek, Qwen, Z.ai and Xiaomi, plus six new providers — all on the /v1/ai/chat endpoint you already use.

We have just added forty-eight new LLM chat models to YepAPI, the largest model refresh we have shipped. It brings the platform up to date with every major lab's current generation — OpenAI's full GPT-6 and GPT-5.6 series, Anthropic's Claude Fable 5.1, Opus 5.5, Opus 5, Sonnet 5 and Haiku 4.5, Google's Gemini 3.8, 3.7 and 3.6 Flash, xAI's Grok 4.7 and 4.6 — and adds six providers that were not on YepAPI before: Sakana AI, Meta's Muse Spark, Cohere, Fireworks, Upstage and Tencent. Every model is callable from the same `/v1/ai/chat` (and OpenAI-compatible `/v1/ai/chat/completions`) endpoint under the same key, with pay-per-token pricing and no waitlist.

What's new

  • OpenAI GPT-6 Astra, Sol and Luna (plus Pro reasoning modes) and the GPT-5.6 Sol, Terra and Luna series
  • Anthropic Claude Fable 5.1, Opus 5.5, Opus 5, Sonnet 5 and Haiku 4.5 — the full Claude 5 generation
  • Google Gemini 3.8, 3.7 and 3.6 Flash and 3.5 Flash Lite — multimodal with audio and video input
  • xAI Grok 4.7 and 4.6; Meta Muse Spark 1.3; Sakana AI Fugu Max and Fugu Ultra v2
  • DeepSeek V4.1 Flash and V4 Pro 0813, Qwen3.8 Max, Flash, Omni Flash and 27B, GLM 5.3 family, MiMo V2.6 family, Seed 2.1 Turbo and Seed-2.0-Code
  • New providers: Cohere Command A+, Fireworks Ember-1, Upstage Solar Pro 4 and Mini 4, NVIDIA Nemotron 3.5 Lightning, Tencent Hy4 preview
  • Short aliases now point at the newest release: `claude-opus` → Opus 5.5, `claude-sonnet` → Sonnet 5, `claude-haiku` → Haiku 4.5, `claude-fable` → Fable 5.1, `gemini-flash` → 3.8 Flash, `grok` → 4.7, `qwen` → Qwen3.8 Max, `glm` → GLM 5.3 Prime, `mimo` → MiMo-V2.6-Pro, `seed` → Seed 2.1 Turbo

Endpoints in this release

AIGPT-6 Astra$14.77 / $73.85 per 1M tokensAIFugu Max$2.95 / $8.86 per 1M tokensAIFugu Ultra v2$7.38 / $44.31 per 1M tokensAIGPT-6 Sol$2.95 / $14.77 per 1M tokensAIGPT-6 Luna$0.15 / $0.74 per 1M tokensAIGPT-6 Astra Pro$14.77 / $73.85 per 1M tokensAIGPT-6 Sol Pro$2.95 / $14.77 per 1M tokensAIGPT-6 Luna Pro$0.15 / $0.74 per 1M tokensAIGPT-5.6 Luna$0.30 / $1.77 per 1M tokensAIGPT-5.6 Luna Pro$0.30 / $1.77 per 1M tokensAIGPT-5.6 Sol$2.95 / $14.77 per 1M tokensAIGPT-5.6 Sol Pro$2.95 / $14.77 per 1M tokensAIGPT-5.6 Terra$2.95 / $17.72 per 1M tokensAIGPT-5.6 Terra Pro$2.95 / $17.72 per 1M tokensAIClaude Fable 5.1$14.77 / $73.85 per 1M tokensAIClaude Opus 5.5$5.91 / $29.54 per 1M tokensAIClaude Opus 5$7.38 / $36.92 per 1M tokensAIClaude Sonnet 5$2.95 / $14.77 per 1M tokensAIClaude Haiku 4.5$1.48 / $7.38 per 1M tokensAIGemini 3.8 Flash$1.05 / $5.85 per 1M tokensAIGemini 3.7 Flash$1.05 / $5.85 per 1M tokensAIGemini 3.6 Flash$1.05 / $5.85 per 1M tokensAIGemini 3.5 Flash Lite$0.44 / $3.69 per 1M tokensAIGrok 4.7$2.36 / $7.09 per 1M tokensAIGrok 4.6$2.95 / $8.86 per 1M tokensAIMuse Spark 1.3$1.85 / $6.28 per 1M tokensAIDeepSeek V4.1 Flash$0.05 / $0.43 per 1M tokensAIDeepSeek V4 Pro 0813$0.37 / $5.17 per 1M tokensAIQwen3.8 Max Prime$5.91 / $17.72 per 1M tokensAIQwen3.8 Max (0902)$2.95 / $8.86 per 1M tokensAIQwen3.8 Flash$0.22 / $0.69 per 1M tokensAIQwen3.8 Omni Flash$0.22 / $0.69 per 1M tokensAIQwen3.8 27B$0.62 / $4.43 per 1M tokensAIGLM 5.3 Prime$4.14 / $13.00 per 1M tokensAIGLM 5.3$0.35 / $1.05 per 1M tokensAIGLM 5.3 Flash$0.06 / $0.74 per 1M tokensAIGLM 5.3 FlashX$0.55 / $1.85 per 1M tokensAIMiMo-V2.6-Pro$0.64 / $1.28 per 1M tokensAIMiMo-V2.6-Flash$0.21 / $0.43 per 1M tokensAIMiMo-V2.6-Pro-UltraSpeed$6.42 / $12.85 per 1M tokensAISeed 2.1 Turbo$0.74 / $3.69 per 1M tokensAISeed-2.0-Code$0.74 / $4.43 per 1M tokensAICommand A+$0.44 / $2.22 per 1M tokensAIEmber-1$4.43 / $22.15 per 1M tokensAISolar Pro 4$0.13 / $0.53 per 1M tokensAISolar Mini 4$0.07 / $0.30 per 1M tokensAINemotron 3.5 Lightning$0.12 / $0.30 per 1M tokensAIHy4 preview$1.23 / $3.69 per 1M tokens

What's new

The headline is the frontier: GPT-6 Astra, Claude Fable 5.1 and Claude Opus 5.5 are the strongest models each lab offers, and Gemini 3.8 Flash and Grok 4.7 are their newest fast tiers. Behind them sits a deep bench of value models — GPT-6 Luna at $0.15 per 1M input tokens, DeepSeek V4.1 Flash at $0.05, GLM 5.3 Flash at $0.06, MiMo-V2.6-Pro at $0.64 for a trillion-parameter omni-modal model — that make it cheap to run agents at scale. Sakana AI's Fugu family brings a different architecture to the platform: a learned multi-agent orchestration system rather than a single dense model.

Aliases updated to the newest release

If you use a family alias, it now resolves to the newest model in that family. `claude-opus` is Opus 5.5, `claude-sonnet` is Sonnet 5, `claude-haiku` is Haiku 4.5, `claude-fable` is Fable 5.1, `gemini-flash` is Gemini 3.8 Flash, `grok` is Grok 4.7, `qwen` is Qwen3.8 Max (0902), `glm` is GLM 5.3 Prime, `mimo` is MiMo-V2.6-Pro and `seed` is Seed 2.1 Turbo. Pin the full model ID (for example `anthropic/claude-opus-4.8`) if you want to stay on a specific release.

How to call them

Set the model field to the full ID or a short alias and everything else stays the same.

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-opus-5.5", "messages": [{"role": "user", "content": "Summarize the trade-offs of event sourcing."}]}'

Pricing

Every model is priced per 1M tokens and listed above; the model pages and the docs billing page show the same numbers. As always you pay only for tokens used, failed calls are never charged, and every call is itemised in your dashboard API Logs.

Try them on your own prompts

Every new account includes $5 in free credit, no card required.

Browse all AI models

Related updates

NEW MODEL
12 new LLM models — GPT-5.5, Claude Opus 4.8 & Fable 5, Gemini 3.5 Flash, Grok 4.3 and more
June 18, 2026

Newer

AI model list prices now show exactly what you are billed

Older

Pricing update on selected SEO, email and Maps endpoints
Back to full changelog