Standard Compute
← All models

Best Model for OpenCode

Claude Sonnet 5.5 is the best model for OpenCode on quality per dollar: it scores 61.8% on Terminal-Bench 4.0 and costs about $5.84 per 100 OpenCode requests on our measured traffic. The most-used model on OpenCode's public usage board is DeepSeek V4.1 Flash, which costs about $0.73 per 100 requests at peak rates and suits high-volume work, though DeepSeek reports 42.3% on Terminal-Bench 4.0 for its October 17 update, up from 31.2%. Claude Opus 5.5 (64.9%) is the step up for the hardest sessions.

Read the full OpenCode review → · updated 2026-10-17

Sources: OpenCode models docs · OpenCode usage board · Terminal-Bench 4.0 leaderboard · Anthropic on Haiku 5.5 · DeepSeek V4.1 Flash release · Cost per request methodology

Run any of these models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

OpenCode setup →See plans
#1Claude Sonnet 5.5Anthropic · $4.40/1M · 1M ctx

Best overall. 61.8% on Terminal-Bench 4.0 and 95.8 on Scale's SWE-Bench Pro V2, with no long-prompt surcharge, which matters in OpenCode, where more than half of the requests we measured sent over 100K input tokens.

Overall 96/100 · Value 59Full breakdown →
#2Claude Opus 5.5Anthropic · $8.80/1M · 1M ctx

Best for long agent runs. #1 on Terminal-Bench 4.0 at 64.9%, for hard refactors and long autonomous sessions. Every rate is double Sonnet 5.5's.

Overall 98/100 · Value 51Full breakdown →
#3Claude Haiku 5.5Anthropic · $0.22/1M · 1M ctx

Best value. Anthropic reports 39.2% on Terminal-Bench 4.0 at $0.10/$0.50 per million tokens. OpenCode sessions grow past 100K tokens often, where Haiku's price steps up five times, so it fits short tasks best.

Overall 82/100 · Value 97Full breakdown →
#4DeepSeek V4.1 FlashDeepSeek · $0.22/1M · 1.0M ctx

Budget pick. The most-used model on OpenCode's usage board in the week to October 13, 2026, with open weights under the MIT license. Half price outside DeepSeek's peak hours.

Overall 77/100 · Value 93Full breakdown →
#5GPT-6.1 SolOpenAI · $4.40/1M · 1.1M ctx

OpenAI pick. 58.2% on Terminal-Bench 4.0 at the same $2/$10 list price as Sonnet 5.5; prompts over 272K tokens bill at $4/$15.

Overall 92/100 · Value 58Full breakdown →
#6GLM 5.3Z.AI · $1.50/1M · 1.0M ctx

Open-weight pick. The top open-weight model on Terminal-Bench 4.0 (41.8%) and 95.6 on Scale's SWE-Bench Pro V2, with a 1M-token context.

Overall 83/100 · Value 69Full breakdown →

What 100 OpenCode requests cost on each pick

A typical request sends 114,859 input tokens, 87% of them read from cache, and a median session runs 16 requests. Measured on OpenCode requests through our gateway (64,668 requests from 68 users), Sep 13 to Oct 12, 2026, priced at each vendor's list rates.

Model100 requestsMedian sessionMonth of regular use
Claude Sonnet 5.5$5.84$0.73$79.06
Claude Opus 5.5$11.69$1.47$158
Claude Haiku 5.5$1.49$0.10$17.91
DeepSeek V4.1 Flash$0.73$0.089$9.58
GPT-6.1 Sol$7.58$0.74$91.20
GLM 5.3$6.28$0.71$97.00

Month of regular use = the median user active on 5 or more days (1,622 requests in 30 days). Methodology · All models ranked by cost per request

Best model for OpenCode under $19, $49 or $99 a month

The highest-rated model whose list-price cost for a month of regular use (1,622 requests) stays under each budget. Heavier months cost proportionally more.

Monthly budgetBest model that fitsEst. month
Under $19Claude Haiku 5.5$17.91
Under $49Claude Haiku 5.5$17.91
Under $99Claude Sonnet 5.5$79.06

"Highest-rated" uses our editorial quality and agentic scores; candidates are current models with a checked vendor price.

FAQ

What is the best model for OpenCode?
Claude Sonnet 5.5 for the best results per dollar (61.8% on Terminal-Bench 4.0), Claude Opus 5.5 for the hardest sessions, and DeepSeek V4.1 Flash for cheap, high-volume work.
Which model do OpenCode users run most?
DeepSeek V4.1 Flash had the most tokens on OpenCode's public usage board (opencode.ai/data) in the week to October 13, 2026. It is cheap and fast; DeepSeek reports 42.3% on Terminal-Bench 4.0 for its October 17 update, up from 31.2%, well below Claude Sonnet 5.5's 61.8%.
Does OpenCode support open-weight models?
Yes. OpenCode uses the AI SDK and Models.dev to support more than 75 providers, plus custom OpenAI-compatible ones, so GLM 5.3, DeepSeek and other open-weight models run hosted or self-hosted.
How much do 100 OpenCode requests cost?
At vendor list prices, 100 average coding-agent requests cost: Claude Sonnet 5.5 $5.84, Claude Opus 5.5 $11.69, Claude Haiku 5.5 $1.49, DeepSeek V4.1 Flash $0.73, GPT-6.1 Sol $7.58, GLM 5.3 $6.28. Measured on real coding-agent traffic through the Standard Compute gateway (Sep 13 to Oct 12, 2026), priced with each request's own token counts and cache reads.
What is the best model for OpenCode on a $19, $49 or $99 monthly budget?
For a month of regular use (1,622 requests, the median in our data), the highest-rated model that fits under $19: Claude Haiku 5.5 (about $17.91); under $49: Claude Haiku 5.5 (about $17.91); under $99: Claude Sonnet 5.5 (about $79.06). Heavier months cost proportionally more.

The agent matters as much as the model. Compare AI agents →

Every model on this page runs on Standard Compute

Standard Compute

Current frontier models Claude Fable 5.1 · GPT-6 Astra

More intelligence
per dollar.

Each step goes to the cheapest model that can do it, on providers we vet for price, uptime and speed, with automatic fallback when one fails.

Compliance
Opt-in rules keep a company, team or key on European or US providers
Privacy
We don’t train on your prompts or store them

Fixed monthly plans from $19 · cancel anytime

7-day fair refund Free trial, no card Billing by Stripe4,100+ agent users