Model releases/10 min read
Muse Wonder API: Meta's $4/$20 Pricing and Setup
Muse Wonder API pricing is $4/$20 per 1M tokens, cached input $0.20, 1M context. Not on RouterPlex yet. Sign up and use live Claude Opus 5.5.
Read the full analysis
Blog
LLM gateway notes for the model layer.
Source-backed RouterPlex research on model pricing, gateway architecture, agent setup, and keeping production AI spend under control.
53
Published notes
7
Research desks
Pricing is checked against primary sources and dated so you can audit the numbers.
Latest research
The research feed
Recent field notes.
Model launches move quickly. The useful details are slower: price thresholds, context limits, protocol compatibility, and the operational tradeoffs hidden below the headline.
Model releases
8 min read
Claude Haiku 5.5 API: $0.10/$0.50 Pricing and Setup
Claude Haiku 5.5 is $0.10/$0.50 per 1M tokens for prompts up to 100K, and $0.50/$2.50 above. Not on RouterPlex yet. Sign up and use live models.
Model releases
13 min read
Aleph Alpha Kolibri: Open-Weight Specs, Benchmarks and Setup
Aleph Alpha Kolibri is a 78B open-weight MoE, 3.46B active, Apache 2.0, English and German, up to 1M tokens. Not on RouterPlex yet.
Model releases
11 min read
Gemini 4 Argon API: Benchmarks, Pricing and Setup (Live)
Gemini 4 Argon is live on RouterPlex as gemini-4-argon: $2/$10 per 1M through 30 Nov 2026, then $4/$20. Google's benchmarks, limits and setup code.
Model releases
8 min read
GPT-6.1 Sol API: Pricing, the 272K Cliff and Setup
GPT-6.1 Sol is live as gpt-6.1-sol. $2/$10 per 1M at or below 272K. Above that the whole request bills $4/$15. Cache reads are $0.16.
Model releases
6 min read
Claude Sonnet 5.5 API: $2/$10 Pricing and Setup
Claude Sonnet 5.5 is $2/$10 per 1M tokens. API id claude-sonnet-5-5. Not on RouterPlex yet. Register for 60+ live models and use it once listed.
Model releases
4 min read
Eleven v4 API Pricing: $0.022 per 1K Characters
Eleven v4 is $0.022 per 1K characters until the pricing page's Oct 12 promo, list $0.08. Model id eleven_v4. Not on RouterPlex yet.
Model releases
4 min read
Eleven v4 Turbo API Pricing: $0.011 per 1K Characters
Eleven v4 Turbo is $0.011 per 1K characters, list $0.04, with a 150 ms median time to first speech on ElevenLabs' chart. Not on RouterPlex yet.
Model releases
6 min read
Claude Opus 5.5 API: $4/$20 Pricing and Setup
Claude Opus 5.5 is $4/$20 per 1M tokens. API id claude-opus-5-5, released 22 Sep 2026. Live on RouterPlex at list price, 0% markup.
Model releases
5 min read
Gemini 3.8 Flash TTS API: Pricing and Setup
Gemini 3.8 Flash TTS is $0.50 text in and $9 audio out per 1M tokens through 31 Dec 2026. Id gemini-3.8-flash-tts. Not on RouterPlex yet.
Model releases
4 min read
Gemini 3.8 Flash-Lite TTS API: Pricing and Setup
Gemini 3.8 Flash-Lite TTS is $0.50 text in and $6 audio out per 1M through 31 Dec 2026. Not on RouterPlex yet. Register for 60+ models.
Model releases
4 min read
Fireworks Ember-1: Pricing, Benchmarks and Setup
Fireworks Ember-1 targets Kimi K3 quality with about 40% fewer tokens. Research preview, 23 Sep 2026. Not on RouterPlex yet. kimi-k3 is live.
Model releases
8 min read
GPT-6 Sol API: Pricing, the 272K Cliff and Setup
GPT-6 Sol API pricing is $2/$10 per 1M tokens at or below 272K. Above that the whole request bills $4/$15. Cache reads are $0.16. Live as gpt-6-sol.
Model releases
7 min read
GPT-6 Luna API: Pricing, the 272K Cliff and Setup
GPT-6 Luna API pricing is $0.10/$0.50 per 1M at or below 272K. Above that the whole request bills $0.20/$0.75. Cache reads are $0.014. ID gpt-6-luna.
Model releases
10 min read
MiMo-V2.6 API: Pro and Flash Pricing and Setup
MiMo-V2.6 Pro API is $0.435/$0.87 per 1M tokens. Flash is $0.14/$0.28. Both are live as mimo-v2.6-pro and mimo-v2.6-flash.
Model releases
7 min read
Grok 4.7 API: Pricing, 500K Context and Setup
Grok 4.7 API pricing is $2 per 1M input and $6 per 1M output tokens, same as 4.6. 500K context, 200K cliff, live as grok-4.7.
Model releases
6 min read
Aikido Altar: Open-Weight Security Model, GLM-5.3 Size and Setup
Aikido Altar is a 328 GB open-weight security LLM from GLM-5.3. CVE 60.4% recall, 4x H200 vLLM. Not on RouterPlex yet. Sign up and wait for the catalog.
Model releases
8 min read
Quiver Arrow 2 API: Pricing, Telos and Setup
Quiver Arrow 2 is $4/$20 per 1M tokens; Arrow 2 Telos is $6/$30 with 1.05M context. SVG generate, vectorize, animate. On RouterPlex once listed.
Model releases
11 min read
Jev API Pricing: Free for a Limited Time
Four decision models, including Jev, are free for a limited time. List price is $0.042 or $0.045 per 1M input. Output is free.
Model releases
8 min read
Gemini 3.8 Live API: Pricing, Extended Thinking and Setup
Gemini 3.8 Live and Live Extended Thinking: native speech-to-speech, $0.005/min in, $0.018/min out, 128K context. On RouterPlex in a few days.
Model releases
5 min read
OpenAI Paused ChatGPT Pro ($200): GPT-6 Astra Is Still on the API
OpenAI paused new $200 ChatGPT Pro signups on 10 Sep 2026. Existing accounts stay. The API is open. Call GPT-6 Astra on RouterPlex.
Developer guides
8 min read
Apple Foundation Models API on iOS 27: Daily Limits, Claude, and GPT
Apple Foundation Models API ships with iOS 27 on 14 Sep. On-device is free. AFM 3 Cloud has daily limits and a future fee. Call Claude and GPT on RouterPlex.
Model releases
7 min read
OpenAI Navier-Stokes Solution: What GPT-6 Astra Actually Did
Did OpenAI solve Navier-Stokes? A finite-time singularity claim, Lean-checked by GPT-6 Astra in 17 hours. The solver is not public; Astra is on RouterPlex.
Agent integrations
6 min read
Override OpenAI Base URL in Cursor with RouterPlex
Cursor Override OpenAI Base URL not working? Fix the /v1 path, blocked localhost, HTTP/2 stalls and the 3.15 input bug, then verify with one test prompt.
Agent integrations
4 min read
Codex CLI Custom Provider with RouterPlex (Responses API)
Point Codex CLI at a custom provider with wire_api = responses. RouterPlex speaks the Responses API Codex uses; chat completions is the wrong adapter.
Model releases
4 min read
GLM-5.3 API: Pricing, Flash Rate and Setup
GLM-5.3 API pricing is $1.40 per 1M input and $4.40 per 1M output. GLM-5.3 Flash is $0.15/$0.50 with vision. Z.ai's Flash promo is not billed here.
Model releases
3 min read
Qwen3.8 Flash API: Pricing, Context Window and Setup
Qwen3.8 Flash API pricing is $0.15 per 1M input and $0.47 per 1M output. Text-only 1M-context sibling of Qwen3.8-Max. Rates and setup.
Model releases
4 min read
Hy4 Preview API: Pricing, Reasoning Tokens and Setup
Hy4 Preview API pricing is $0.834 per 1M input and $2.501 per 1M output. Tencent preview; it spends heavily on reasoning tokens. Rates and setup.
Model releases
3 min read
DeepSeek V4 Flash Vision API: Pricing, Off-Peak Rate and Setup
DeepSeek V4 Flash Vision API pricing is $0.22 per 1M input and $0.66 per 1M output at all hours (DeepSeek off-peak). Experimental vision preview.
Model releases
4 min read
Muse Spark Contributor API: $0.10/$0.20 and the Training Licence
Muse Spark 1.2 and 1.3 Contributor API pricing is $0.10 per 1M input and $0.20 per 1M output because Meta may train on your prompts. No tools. Never a default.
Model releases
5 min read
GPT-6 Astra API: Pricing, the 272K Cliff and Setup
GPT-6 Astra API pricing is $10 per 1M input and $50 per 1M output below 272K tokens. Above 272K the whole request bills $20/$75. Rates, 922K input and setup.
Model releases
5 min read
Gemini 3.8 Flash API: Pricing, Intro Rate and Setup
Gemini 3.8 Flash API pricing is $0.75 per 1M input and $3.75 per 1M output through 31 Dec 2026, then $1.50/$7.50. 1M context, 65K output, and setup.
Model releases
5 min read
Grok 4.6 API: Pricing, the 200K Cliff and Setup
Grok 4.6 API pricing is $2 per 1M input and $6 per 1M output tokens, with cached input at $0.50 — up from $0.30 on Grok 4.5. Rates, 500K context and setup.
Model releases
6 min read
Qwen3.8-Max API: Pricing, Context Window and Setup
Qwen3.8-Max API pricing is $2 per 1M input and $6 per 1M output tokens. See the 1M context window, image input, cost per agent turn, and setup.
API fundamentals
8 min read
What Is an OpenAI-Compatible API? Endpoints, SDK Setup, and Provider Switching
Learn what OpenAI-compatible means, which endpoints and SDK settings carry over, what can break, and how to switch providers with curl, Python, and JavaScript.
Model releases
5 min read
Grok API Pricing: Every Model, Rate and the 200K Cliff
Grok API pricing: Grok 4.7, 4.6 and 4.5 are $2 per 1M input and $6 per 1M output, doubling above a 200K prompt. Full xAI rate table, cache notes, and setup.
Model releases
6 min read
Claude Opus 5 API: Pricing, Context and Setup
Claude Opus 5 API pricing is $5 per 1M input and $25 per 1M output tokens, the same rate as Opus 4.8. See its 1M context, effort tiers, and setup.
Gateway economics
6 min read
Claude Code Pricing: Pro, Max, and API Costs
Claude Code costs $20/month with Pro, $100 or $200 with Max, or pay-as-you-go API rates. Compare plans, limits, and the right billing route.
Developer guides
4 min read
Install Claude Code on macOS, Windows, and Linux
Install Claude Code with the current native installer on macOS, Windows, Linux, or WSL. Verify the CLI, fix PATH errors, authenticate, and update safely.
Developer guides
7 min read
Claude Code Alternatives (2026): 8 Coding Agents Compared
OpenCode is the closest Claude Code alternative for terminal work. Compare 8 agents on interface, models, open source, and how you pay.
Gateway architecture
8 min read
Best LLM Gateways for Developers (2026): 11 Compared
Compare 11 LLM gateways: RouterPlex, OpenRouter, LLM Gateway, Vercel, Requesty, Fireworks, Together, LiteLLM, Portkey, Helicone, AgentRouter.
Gateway economics
11 min read
OpenRouter Alternatives (2026): 9 Options Compared
Compare 9 OpenRouter alternatives: RouterPlex, LLM Gateway, Requesty, Vercel, LiteLLM and more. $100 credit math, fees, and which wallet fits.
Model releases
6 min read
Kimi K3 API: Pricing, Context Window and Setup
Official Kimi K3 API pricing: $3/$15 per 1M (cache-hit $0.30). Cheapest Kimi K3 API is that list rate with no 5.5% top-up fee. 1M context, setup.
Model releases
4 min read
GPT-5.6 API Pricing: Sol vs Terra vs Luna
GPT-5.6 Sol API pricing is $5/$30 per 1M on RouterPlex; Terra $2/$12, Luna $0.20/$1.20. OpenAI lists a Sol promo at $4/$20; we bill catalog rates.
Model releases
4 min read
Claude Fable 5 API: Pricing, Context and Setup
Claude Fable 5 API pricing is $10 per 1M input and $50 per 1M output tokens. See its 1M context, 128K output, vision support and RouterPlex setup.
Agent integrations
3 min read
OpenClaw Custom Provider Setup with RouterPlex
Connect OpenClaw to RouterPlex as an OpenAI-compatible custom provider, choose Claude or Gemini models, verify the route, and cap agent spending.
Agent integrations
2 min read
OpenCode Custom Provider Setup for Claude, GPT, and Gemini
Add RouterPlex to OpenCode with the OpenAI-compatible provider package, register model IDs, select a model, and set a hard API-key budget.
Agent integrations
3 min read
Cline OpenAI-Compatible API Setup with RouterPlex
Configure Cline's OpenAI Compatible provider with RouterPlex, enter the base URL and model ID, verify the connection, and limit agent spend.
Agent integrations
2 min read
Aider OpenAI-Compatible API Setup with RouterPlex
Point Aider at RouterPlex with OPENAI_API_BASE, choose Claude or GPT through the openai/ model prefix, and protect the coding session with a key budget.
Gateway economics
7 min read
Do OpenRouter Credits Expire? Fees and the 365-day Rule
OpenRouter may expire unused credits 365 days after purchase; its COO says it doesn't in practice. Buying costs 5.5% ($0.80 min), refunds only within 24h.
Spend safety
6 min read
Fix an OpenRouter 402 Error and Negative Balance
Fix each OpenRouter 402 message: "requires more credits, or fewer max_tokens", "never purchased credits" and a negative balance. Plus how to stop retry loops.
Developer guides
9 min read
Claude Code Router (CCR): Install and Route Any Model
Install Claude Code Router (CCR), add a provider, and send Claude Code to DeepSeek, Qwen, Kimi, or a hosted key. Skip CCR when one gateway is enough.
Gateway architecture
5 min read
LiteLLM Alternatives: Managed Gateways vs Self-Hosting
Compare LiteLLM alternatives across self-hosted proxies, managed BYOK gateways, and prepaid model access, including operations, billing, and security.
Test the findings
Run the smallest paid experiment.
Add $5, cap the key, and verify the result with your own workload. No subscription, and credit never expires — a first top-up of $25+ is matched with $25 extra.