TheRouter.aiTheRouter.ai

Announcement · 2026-05-05

Qwen 3.6 Release, May 2026 — Kimi K2.6, Gemma 4 & Mistral Small 4

Qwen 3.6 27B (MoE, 262K context, May 2026) plus three more new models on TheRouter — Kimi K2.6 ties GPT-5.5 on coding, Gemma 4 ships Apache 2.0, and Mistral unifies reasoning, vision, and agentic coding into Small 4. All available via OpenAI-compatible API.

What shipped

Between late March and late April 2026, three model families dropped meaningful new releases. We verified each one end-to-end against its primary upstream provider and added the following five aliases to the gateway. Existing aliases are unchanged — the rollout is strictly additive (we ran a byte-level snapshot regression gate to prove every pre-existing model behaves identically).

Moonshot — Kimi K2.6

Released 2026-04-20. Kimi K2.6 is Moonshot AI's 1T-parameter Mixture-of-Experts flagship. It ties GPT-5.5 on coding benchmarks at open-weight pricing, and the agent-swarm subsystem now scales to 300 sub-agents and 4,000 coordinated steps (up from 100 / 1,500 in K2.5). Customer alias moonshot/kimi-k2.6.

Alibaba — Qwen 3.6 27B

Released 2026-04-16. The 3.6 generation is hybrid multimodal with a 262K context window and significantly stronger repo-level coding compared to the 3.x line. We surface the 27B MoE variant under alias qwen/qwen3.6-27b, routed via SiliconFlow and Aliyun Bailian upstream.

Google — Gemma 4 (Apache 2.0)

Released 2026-04-02. Two server-class sizes are live: google/gemma-4-31b-it (dense, Arena #3 open-weight) and google/gemma-4-26b-a4b-it (Mixture-of-Experts with 4B active per token, Arena #6). Both are Apache 2.0 — the most permissive license Google has shipped a Gemma series under. Both support text + image input.

Mistral — Small 4

Released 2026-03. A single 119B MoE (6B active) model that unifies the capabilities of three earlier specialists: Magistral (reasoning), Pixtral (multimodal), and Devstral (agentic coding). Tools, vision, JSON mode all on by default. Alias mistral/mistral-small-4.

Mistral — Voxtral TTS

Voxtral TTS is not yet routable on TheRouter; we'll announce when a viable upstream lands.

How to use

The new aliases work via TheRouter's OpenAI-compatible API:

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot/kimi-k2.6",
    "messages": [{"role": "user", "content": "Write a Rust quicksort"}],
    "max_tokens": 1024
  }'

Pricing (USD per million tokens)

ModelInputOutput
moonshot/kimi-k2.6$1.14$5.40
qwen/qwen3.6-27b$0.24$0.96
google/gemma-4-31b-it$0.36$0.60
google/gemma-4-26b-a4b-it$0.24$0.48
mistral/mistral-small-4$0.24$0.72

Prices shown are launch-time figures; see each model page for the current billed rate.

Existing models unchanged

Every model in our catalog from before this rollout behaves identically. We ship a snapshot regression test that asserts byte-level equivalence on the 181 pre-existing aliases (every observable field — pricing, modality, capabilities, routes — must match). The test passes.

Coming next

One follow-up is tracked but not bundled here: google/gemma-4-e4b (effective-4B, on-device target — provider hosting not yet confirmed). We'll surface it in a future model wave once a viable upstream lands.

Try the new aliases on dashboard.therouter.ai or via API. Feedback welcome at hello@therouter.ai.

Customer Support